@phdthesis{Tomashevich2016, author = {Tomashevich, Victor}, title = {Fault Tolerance Aspects of Virtual Massive MIMO Systems}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-4047}, school = {Universit{\"a}t Passau}, pages = {183}, year = {2016}, abstract = {Employment of a very large number of antennas is seen as the key technology to provide future users with very high data rates. At the same time, the implementation complexity will rise due to large memories required and sophisticated signal processing algorithms employed. Continuous technology downscaling allows implementation of such complex digital designs. At the same time, its inherent variability and vulnerability to physical disturbances violate the assumption of perfectly reliable hardware operation. This work considers Unique Word OFDM which represents the alternative to the standard Cyclic Prefix OFDM providing superior detection quality. The generalization of Unique Word OFDM to a MIMO system is performed which allows interpretation as a virtual massive MIMO system with only few physical antennas. Detection methods for the introduced generalization are discussed and their performance is quantified. Because of the large memory size required, linear detection represents the cost and performance effective solution. The possible memory errors due to radiation effects or voltage scaling are addressed and the nonlinear MMSE detection algorithm is proposed. This algorithm keeps track of the memory errors and is able to significantly mitigate their effect on the quality of the estimated data. Apart of memory issues, reliability of the actual computational hardware which constitutes the receiver is of concern in this work. An own implementation of the MMSE Sorted Givens Rotations is subjected to transient fault injection. The impact of faults in various parts of the implemented circuit on the detection performance is quantified. Most vulnerable components of the implemented circuit in terms of reliability are identified. Security is another major address of this work, since most current implementations include cryptographic devices. Fault-based attacks on such systems are known to be able to extract the secret key in feasible time. The remaining part of this work addresses such fault injection-based malicious attacks. Countermeasures based on a combination of information and hardware redundancy are considered. Recently introduced robust codes target such attacks by providing guaranteed detection capability. The performance of these codes is assessed by application to actual cryptographic and general purpose circuits. The work introduces metrics that help to identify fault locations in the circuit which could escape detection with high probability. These locations are targeted by transistor resizing that renders fault injection unfeasible.}, subject = {MIMO}, language = {en} } @phdthesis{Jiang2016, author = {Jiang, Jie}, title = {Delay Testing in Nanoscale Technology under Process Variations}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-4229}, school = {Universit{\"a}t Passau}, year = {2016}, abstract = {In modern CMOS technology, process variations have significantly increased impact on the circuit behavior with continuously scaled transistor sizes. Manufactured devices tend to have different performances due to parameter variations during manufacturing and in the operating context. Conventional tests generated regardless of variations could fail to rule out devices with low performance and even functional failure caused by extreme variations; the unreliability in shipped products is in turn raised. To tackle the problem, many existing test approaches have focused on identifying and testing a number of critical paths in the circuit, and aimed at the efficiency of the searching process. However, the statistical circuit model, which better describes the circuit timing behavior under variations, is not yet sufficiently investigated and employed by existing testing methodologies. This thesis work proposes Opt-KLPG and MIRID, which can be utilized by a statistical delay testing flow. Opt-KLPG—a K Longest Paths Generation (KLPG) algorithm for optimal solutions under memory constraints—can pin-pointedly generate tests for small delay defects, which are common small timing deviations under process variations, based on the traditional KLPG algorithm. In contrast to KLPG, Opt-KLPG guarantees the optimality of the solution (the K longest sensitizable paths indeed). MIRID is a mixed-mode timing-aware simulator, incorporating effects of power-supply noise and combining an event-driven logic simulation engine with interfaces to provided electrical models. MIRID aims at evaluating delay tests in presence of process variations efficiently yet accurately, by performing logic simulation at the gate level while determining the gate delays using simplified electrical modes. The electrical models applied by the simulator focus on the IR drop effect. Electrical parameters mainly contributing to the effect are incorporated into the model. The simulator is generic and flexible to be adapted by modifying the interfaces with minor effort. Both applications were verified in various aspects by experiments for academical/industrial circuits, and turned out to have satisfiable effectiveness and performance.}, subject = {CMOS}, language = {en} } @phdthesis{Alsarem2016, author = {Alsarem, Mazen}, title = {Semantic Snippets via Query-Biased Ranking of Linked Data Entities}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3959}, school = {Universit{\"a}t Passau}, pages = {148 S.}, year = {2016}, abstract = {In our knowledge-driven society, the acquisition and the transfer of knowledge play a principal role. Web search engines are somehow tools for knowledge acquisition and transfer from the web to the user. The search engine results page (SERP) consists mainly of a list of links and snippets (excerpts from the results). The snippets are used to express, as efficiently as possible, the way a web page may be relevant to the query. As an extension of the existing web, the semantic web or "web 3.0" is designed to convert the presently available web of unstructured documents into a web of data consumable by both human and machines. The resulting web of data and the current web of documents coexist and interconnect via multiple mechanisms, such as the embedded structured data, or the automatic annotation. In this thesis, we introduce a new interactive artifact for the SERP: the "Semantic Snippet". Semantic Snippets rely on the coexistence of the two webs to facilitate the transfer of knowledge to the user thanks to a semantic contextualization of the user's information need. It makes apparent the relationships between the information need and the most relevant entities present in the web page. The generation of semantic snippets is mainly based on the automatic annotation of the LOD1's entities in web pages. The annotated entities have different level of impor- tance, usefulness and relevance. Even with state of the art solutions for the automatic annotations of LOD entities within web pages, there is still a lot of noise in the form of erroneous or off-topic annotations. Therefore, we propose a query-biased algorithm (LDRANK) for the ranking of these entities. LDRANK adopts a strategy based on the linear consensual combination of several sources of prior knowledge (any form of con- textual knowledge, like the textual descriptions for the nodes of the graph) to modify a PageRank-like algorithm. For generating semantic snippets, we use LDRANK to find the more relevant entities in the web page. Then, we use a supervised learning algorithm to link each selected entity to excerpts from the web page that highlight the relationship between the entity and the original information need. In order to evaluate our semantic snippets, we integrate them in ENsEN (Enhanced Search Engine), a software system that enhances the SERP with semantic snippets. Finally, we use crowdsourcing to evaluate the usefulness and the efficiency of ENsEN.}, subject = {World Wide Web 3.0}, language = {en} } @phdthesis{Berndl2018, author = {Berndl, Emanuel}, title = {Embedding a Multimedia Metadata Model into a Workflow-driven Environment Using Idiomatic Semantic Web Technologies}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-6708}, school = {Universit{\"a}t Passau}, pages = {xix, 301 Seiten}, year = {2018}, abstract = {The Semantic Web exists for about 20 years by now, but its applicability as well as its presence does not live up to the standards of its original idea. Incorporated Semantic Web Technologies do have an initial barrier to learn and apply, which can discourage many potential users. This leads to less available data overall in addition to decreased data quality. This work solves parts of the aforementioned problem by supporting idiomatic entry to those Semantic Web Technologies, allowing for "easier" accessibility and usability. Anno4j is a Java library that implements a form of Object-Relational Mapping for RDF data. With its application, RDF data can be created via a mapping by simply instantiating Java objects - an object-oriented programming concept the user is familiar with. On the other side, requesting persisted data is supported by a path-based querying possibility, while other features like transactional behaviour, code generation, and automated validation of input contribute to a more effective, comprehensive, and straightforward usage. A use-case is provided by the MICO Platform, a centralized software instance that connects autonomous multimedia extractors in a workflow-driven fashion. This leads to a rich metadata background for the inserted multimedia files, enabling them to be used in diverse scenarios as well as unlocking yet hidden semantics. For this task it was necessary to design and implement a metadata model that is able to aggregate and merge the varying extractor results under a common denominator: the MICO Metadata Model. The results of this work allow the use case to incorporate idiomatic Semantic Web Technologies which are then usable natively by non-Semantic Web experts. Additionally, an increase has been achieved in forms of data integration, synchronisation, integrity and validity, as well as an overall more comprehensive and rich implementation of the multimedia extractors.}, subject = {Multimedia}, language = {en} } @phdthesis{Awwad2018, author = {Awwad, Tarek}, title = {Context-Aware Worker Selection For Efficient Quality Control In Crowdsourcing}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-7409}, school = {Universit{\"a}t Passau}, pages = {106 Seiten}, year = {2018}, abstract = {In the last decade, crowdsourcing has proved its ability to address large scale data collection tasks, such as labeling large data sets, at a low cost and in a short time. However, the performance and behavior variability between workers as well as the variability in task designs and contents, induce an unevenness in the quality of the produced contributions and, thus, in the final output quality. In order to maintain the effectiveness of crowdsourcing, it is crucial to control the quality of the contributions. Furthermore, maintaining the efficiency of crowdsourcing requires the time and cost overhead related to the quality control to be at its lowest. While effective, current quality control techniques such as contribution aggregation, worker selection, context-specific reputation systems, and multi-step workflows, suffer from fairly high time and budget overheads and from their dependency on prior knowledge about individual workers. In this thesis, we address this challenge by leveraging the similarity between completed and incoming tasks as well as the correlation between the worker declarative profiles and their performance in previous tasks in order to perform an efficient task-aware worker selection. To this end, we propose CAWS (Context AwareWorker Selection) method which operates in two phases; in an offline phase, completed tasks are clustered into homogeneous groups for each of which the correlation with the workers declarative profile is learned. Then, in the online phase, incoming tasks are matched to one of the existing clusters and the correspondent, previously inferred profile model is used to select the most reliable online workers for the given task. Using declarative profiles helps eliminate any probing process, which reduces the time and the budget while maintaining the crowdsourcing quality. Furthermore, the set of completed tasks, when compared to a probing task split, provides a larger corpus from which a more precise profile model can be learned. This translates to a better selection quality, especially for harder tasks. In order to evaluate CAWS, we introduce CrowdED (Crowdsourcing Evaluation Dataset), a rich dataset to evaluate quality control methods and quality-driven task vectorization and clustering. The generation of CrowdED relies on a constrained sampling approach that allows to produce a task corpus which respects both, the budget and type constraints. Beside helping in evaluating CAWS, and through its generality and richness, CrowdED helps in plugging the benchmarking gap present in the crowdsourcing quality control community. Using CrowdED, we evaluate the performance of CAWS in terms of the quality of the worker selection and in terms of the achieved time and budget reduction. Results shows the following: first, automatic grouping is able to achieve a learning quality similar to job-based grouping. And second, CAWS is able to outperform the state-of-the-art profile-based worker selection when it comes to quality. This is especially true when strong budget and time constraints are present on the requester side. Finally, we complement our work by a software contribution consisting of an open source framework called CREX (CReate Enrich eXtend). CREX allows the creation, the extension and the enrichment of crowdsourcing datasets. It provides the tools to vectorize, cluster and sample a task corpus to produce constrained task sets and to automatically generate custom crowdsourcing campaign sites.}, subject = {Qualit{\"a}tssicherung}, language = {en} } @phdthesis{Kolesnikov2019, author = {Kolesnikov, Sergiy}, title = {Feature Interactions in Configurable Software Systems}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-6739}, school = {Universit{\"a}t Passau}, pages = {ix, 140 Seiten}, year = {2019}, abstract = {Software has become an important part of our life. Therefore, the number of different applications scenarios and user requirements of software systems grows rapidly. To satisfy these requirements, software vendors build configurable software systems that can be tailored to diverse needs without rebuilding them from scratch, which reduces costs and development time. Despite considerable advances in software engineering, which allow building high-quality configurable software systems, some challenges remain. One of these challenges is the feature interaction problem that arises when parts (features), from which a configurable system is composed, interact in unexpected ways, and inadvertently change the behavior or quality attributes (such as performance) of the system. The goal of this dissertation is to systematically study the nature of feature interactions, their causes, their influence on performance of configurable systems, and, based on empirical results, suggest ways of improving techniques for detecting and predicting feature interactions. More specifically, we compared and evaluated different strategies for the analysis of configurable software systems. The results of our evaluation complement empirical data from previous work about how different analysis strategies for configurable software systems compare with respect to different aspects, such as performance. These results shall be used to develop effective and scalable techniques and tools for analysis of configurable software including feature-interaction detection and prediction techniques and tools. Technically, we used a machine-learning technique to quantify the influence of feature interactions on performance of real-world configurable systems. We studied the characteristics of interactions that have the largest influence on performance and found that interactions among few features have higher influence than interactions among many features. With a growing number of interacting features, the influence of the corresponding interactions decreases consistently. This implies that interactions involving multiple features can be ignored in practice because of their marginal influence on performance. We also investigated the causes of the interactions and were able to identify several patterns that link these interactions to the architecture of the systems: For example, we found that if a data processing system consisted of multiple features that processed the same data in sequence then these features interacted. The identified patterns can help to anticipate performance interactions already at an early development stage when a system's architecture is designed. Furthermore, considering that control-flow interactions (observable at the level of control flow among features) are easier to detect than performance interactions (externally observable through measuring performance of different combinations of features), we conducted a case study on two configurable systems. In this case study, we investigated a possible relation among control-flow feature interactions and performance feature interactions. We also discussed how this relation can be exploited by interaction detection and performance prediction techniques to make them more time efficient and precise. Our case study on two real-world configurable systems revealed that a relation indeed exists, and we were able to show how it can be used to reduce the search space of possibly existing performance interactions. The study can serve as a blueprint for further studies that can rely on our conceptual framework for investigating relations among external and internal interactions. Overall, the contribution of this dissertation consists of scientific and technical insights, practical tool implementations, empirical evaluations, and case studies that advance the current state of research in the area of feature interactions in configurable software systems. In particular, we provide insights into the causes of feature interactions and their influence on performance of real-world configurable systems (e.g., interaction patterns, decreasing influence of interactions with growing number of involved features). Our results also suggest ways of improving techniques for detecting and predicting feature interactions (e.g., ignoring interactions among multiple features, reducing the search space based on relations among interactions).}, subject = {Softwareentwicklung}, language = {en} } @inproceedings{BergerReiserSousaetal.2019, author = {Berger, Christian and Reiser, Hans P. and Sousa, Jo{\~a}o and Bessani, Alysson}, title = {Resilient Wide-Area Byzantine Consensus Using Adaptive Weighted Replication}, series = {38th IEEE International Symposium on Reliable Distributed Systems (SRDS 2019)}, booktitle = {38th IEEE International Symposium on Reliable Distributed Systems (SRDS 2019)}, publisher = {IEEE Xplore}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-7537}, pages = {10 Seiten}, year = {2019}, abstract = {In geo-replicated systems, the heterogeneous latencies of connections between replicas limit the system's ability to achieve fast consensus. State machine replication (SMR) protocols can be refined for their deployment in wide-area networks by using a weighting scheme for active replication that employs additional replicas and assigns higher voting power to faster replicas. Utilizing more variability in quorum formation allows replicas to swifter proceed to subsequent protocol stages, thus decreasing consensus latency. However, if network conditions vary during the system's lifespan or faults occur, the system needs a solution to autonomously adjust to new conditions. We incorporate the idea of self-optimization into geographically distributed, weighted replication by introducing AWARE, an automated and dynamic voting weight tuning and leader positioning scheme. AWARE measures replica-replica latencies and uses a prediction model, thriving to minimize the system's consensus latency. In experiments using different Amazon EC2 regions, AWARE dynamically optimizes consensus latency by self-reliantly finding a fast weight configuration yielding latency gains observed by clients located across the globe.}, language = {en} } @inproceedings{BergerReiser2018, author = {Berger, Christian and Reiser, Hans P.}, title = {Scaling Byzantine Consensus: A Broad Analysis}, series = {SERIAL'18 Proceedings of the 2nd Workshop on Scalable and Resilient Infrastructures for Distributed Ledgers}, booktitle = {SERIAL'18 Proceedings of the 2nd Workshop on Scalable and Resilient Infrastructures for Distributed Ledgers}, publisher = {ACM}, address = {New York, NY, USA}, isbn = {978-1-4503-6110-1}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-7526}, pages = {6 Seiten}, year = {2018}, abstract = {Blockchains and distributed ledger technology (DLT) that rely on Proof-of-Work (PoW) typically show limited performance. Several recent approaches incorporate Byzantine fault-tolerant (BFT) consensus protocols in their DLT design as Byzantine consensus allows for increased performance and energy efficiency, as well as it offers proven liveness and safety properties. While there has been a broad variety of research on BFT consensus protocols over the last decades, those protocols were originally not intended to scale for a large number of nodes. Thus, the quest for scalable BFT consensus was initiated with the emerging research interest in DLT. In this paper, we first provide a broad analysis of various optimization techniques and approaches used in recent protocols to scale Byzantine consensus for large environments such as BFT blockchain infrastructures. We then present an overview of both efforts and assumptions made by existing protocols and compare their solutions.}, language = {en} } @phdthesis{Kell2019, author = {Kell, Christian}, title = {A Structure-based Attack on the Linearized Braid Group-based Diffie-Hellman Conjugacy Problem in Combination with an Attack using Polynomial Interpolation and the Chinese Remainder Theorem}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-6476}, school = {Universit{\"a}t Passau}, pages = {xi, 209 Seiten}, year = {2019}, abstract = {This doctoral thesis is dedicated to improve a linear algebra attack on the so-called braid group-based Diffie-Hellman conjugacy problem (BDHCP). The general procedure of the attack is to transform a BDHCP to the problem of solving several simultaneous matrix equations. A first improvement is achieved by reducing the solution space of the matrix equations to matrices that have a specific structure, which we call here the left braid structure. Using the left braid structure the number of matrix equations to be solved reduces to one. Based on the left braid structure we are further able to formulate a structure-based attack on the BDHCP. That is to transform the matrix equation to a system of linear equations and exploiting the structure of the corresponding extended coefficient matrix, which is induced by the left braid structure of the solution space. The structure-based attack then has an empirically high probability to solve the BDHCP with significantly less arithmetic operations than the original attack. A third improvement of the original linear algebra attack is to use an algorithm that combines Gaussian elimination with integer polynomial interpolation and the Chinese remainder theorem (CRT), instead of fast matrix multiplication as suggested by others. The major idea here is to distribute the task of solving a system of linear equations over a giant finite field to several much smaller finite fields. Based on our empirically measured bounds for the degree of the polynomials to be interpolated and the bit size of the coefficients and integers to be recovered via the CRT, we conclude an improvement of the run time complexity of the original algorithm by a factor of n^8 bit operations in the best case, and still n^6 in the worst case.}, subject = {Kryptologie}, language = {en} } @phdthesis{Tueno2020, author = {Tueno, Anselme}, title = {Multiparty Protocols for Tree Classifiers}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-8251}, school = {Universit{\"a}t Passau}, pages = {xvii, 171 Seiten}, year = {2020}, abstract = {Cryptography is the scientific study of techniques for securing information and communication against adversaries. It is about designing and analyzing encryption schemes and protocols that protect data from unauthorized reading. However, in our modern information-driven society with highly complex and interconnected information systems, encryption alone is no longer enough as it makes the data unintelligible, preventing any meaningful computation without decryption. On the one hand, data owners want to maintain control over their sensitive data. On the other hand, there is a high business incentive for collaborating with an untrusted external party. Modern cryptography encompasses different techniques, such as secure multiparty computation, homomorphic encryption or order-preserving encryption, that enable cloud users to encrypt their data before outsourcing it to the cloud while still being able to process and search on the outsourced and encrypted data without decrypting it. In this thesis, we rely on these cryptographic techniques for computing on encrypted data to propose efficient multiparty protocols for order-preserving encryption, decision tree evaluation and kth-ranked element computation. We start with Order-preserving encryption (OPE) which allows encrypting data, while still enabling efficient range queries on the encrypted data. However, OPE is symmetric limiting, the use case to one client and one server. Imagine a scenario where a Data Owner (DO) outsources encrypted data to the Cloud Service Provider (CSP) and a Data Analyst (DA) wants to execute private range queries on this data. Then either the DO must reveal its encryption key or the DA must reveal the private queries. We overcome this limitation by allowing the equivalent of a public-key OPE. Decision trees are common and very popular classifiers because they are explainable. The problem of evaluating a private decision tree on private data consists of a server holding a private decision tree and a client holding a private attribute vector. The goal is to classify the client's input using the server's model such that the client learns only the result of the classification, and the server learns nothing. In a first approach, we represent the tree as an array and execute only d interactive comparisons (instead of 2 d as in existing solutions), where d denotes the depth of the tree. In a second approach, we delegate the complete tree evaluation to the server using somewhat or fully homomorphic encryption where the ciphertexts are encrypted under the client's public key. A generalization of a decision tree is a random forest that consists of many decision trees. A classification with a random forest evaluates each decision tree in the forest and outputs the classification label which occurs most often. Hence, the classification labels are ranked by their number of occurrences and the final result is the best ranked one. The best ranked element is a special case of the kth-ranked element. In this thesis, we consider the secure computation of the kth-ranked element in a distributed setting with applications in benchmarking and auctions. We propose different approaches for privately computing the kth-ranked element in a star network, using either garbled circuits or threshold homomorphic encryption.}, subject = {Mathematik}, language = {en} } @phdthesis{Taubmann2020, author = {Taubmann, Benjamin}, title = {Improving Digital Forensics and Incident Analysis in Production Environments by Using Virtual Machine Introspection}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-8319}, school = {Universit{\"a}t Passau}, pages = {ix, 153 Seiten}, year = {2020}, abstract = {Main memory forensics and its special form, virtual machine introspection (VMI), are powerful tools for digital forensics and can be used to improve the security of computer-based systems. However, their use in production systems is often not possible. This work identifies the causes and offers practical solutions to apply these techniques in cloud computing and on mobile devices to improve digital forensics and incident analysis. Four key challenges must be tackled. The first challenge is that many existing solutions are not reproducible, for example, because the corresponding software components are not available, obsolete or incompatible. The use of these tools is also often complex and can lead to a crash of the system to be monitored in case of incorrect use. To solve this problem, this thesis describes the design and implementation of Libvmtrace, which is a framework for the introspection of Linux-based virtual machines. The focus of the developed design is to implement frequently used methods in encapsulated modules so that they are easy for developers to use, optimize and test. The second challenge is that many production systems do not provide an interface for main memory forensics and virtual machine introspection. To address this problem, this thesis describes possible solutions for how such an interface can be implemented on mobile devices and in cloud environments designed to protect main memory from unprivileged access. We discuss how cold boot attacks, the ARM TrustZone and the hypervisor of cloud servers can be used to acquire data from storage. The third challenge is how to reconstruct information from main memory efficiently. This thesis describes how these questions can be solved by employing two practical examples. The first example involves extracting the keys of encrypted TLS connections from the main memory of applications to decrypt network traffic without affecting the performance of the monitored application. The TLSKex and DroidKex architecture describe two approaches to localize the keys efficiently with the help of semantic knowledge in the main memory of applications. The second example discusses how to monitor and document SSH sessions of potential attackers from outside of a virtual machine. It is important that the monitoring routines are not noticed by an attacker. To achieve this, we evaluate how to optimize the performance of the monitoring mechanism. The fourth challenge is how to deal with the performance degradation caused by introspection in productive systems. This thesis discusses how this can be achieved using the example of a SIEM system. To reduce the performance overhead, we describe how to configure the monitoring routine to collect only the information needed to detect incidents. Also, we describe two approaches that permit the monitoring routine to be dynamically adjusted at runtime to extract more information if necessary so that incidents can be better analyzed.}, subject = {Computerforensik}, language = {en} } @phdthesis{Kurz2019, author = {Kurz, Thomas}, title = {Adapting Semantic Web Information Retrieval to Multimedia}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-8276}, school = {Universit{\"a}t Passau}, pages = {xvi, 206 Seiten}, year = {2019}, abstract = {The amount of audio, video and image data on the Web is immensely growing, which leads to data management problems based on the hidden character of Multimedia. Therefore the interlinking of semantic concepts and media data with the aim to bridge the gap between the Internet of documents and the Web of Data has become a common practice. However, the value of connecting media to its semantic meta data is limited due to lacking access methods and the absence of an adapted query language specialized for media assets and fragments. This thesis aims to extend the standard query language for the Semantic Web (SPARQL) with media specific concepts and functions. The main contributions of the work are an exhaustive survey on Multimedia query languages of the last 3 decades, the SPARQL extension specification itself and an approach for the efficient evaluation of the new query concepts. Additionally I elaborate and evaluate a meta data based media fragment similarity approach, which provides a basis for further language extensions.}, subject = {Semantic Web}, language = {en} } @phdthesis{Ehlers2015, author = {Ehlers, Christoph}, title = {Top-k Semantic Caching}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3055}, school = {Universit{\"a}t Passau}, pages = {266}, year = {2015}, abstract = {The subject of this thesis is the intelligent caching of top-k queries in an environment with high latency and low throughput. In such an environment, caching can be used to reduce network traffic and improve response time. Slow database connections of mobile devices and to databases, which have been offshored, are practical use cases. A semantic cache is a query-based cache that caches query results and maintains their semantic description. It reuses partial matches of previous query results. Each query that is processed by the semantic cache is split into two disjoint parts: one that can be completely answered with tuples of the cache probe query, and another that requires tuples to be transferred from the server (remainder query). Existing semantic caches do not support top-k queries, i.e., ordered and limited queries. In this thesis, we present an innovative semantic cache that naturally supports top-k queries. The support of top-k queries in a semantic cache has considerable effects on cache elements, operations on cache elements -- like creation, difference, intersection, and union -- and query answering. Hence, we introduce new techniques for cache management and query processing. They enable the semantic cache to become a true top-k semantic cache. In addition, we have developed a new algorithm that can estimate the lower bounds of query results of sorted queries using multidimensional histograms. Using this algorithm, our top-k semantic cache is able to pipeline partial query results of top-k queries. Thereby, query execution performance can be significantly increased. We have implemented a prototype of a top-k semantic cache called IQCache (Intelligent Query Cache). An extensive and thorough evaluation with various benchmarks using our prototype demonstrates the applicability and performance of top-k semantic caching in practice. The experiments prove that the top-k semantic cache invariably outperforms simple hash-based caching strategies and scales very well.}, subject = {Semantisches Caching}, language = {en} } @phdthesis{Braun2015, author = {Braun, Bastian}, title = {Web-based Secure Application Control}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3048}, school = {Universit{\"a}t Passau}, year = {2015}, abstract = {The world wide web today serves as a distributed application platform. Its origins, however, go back to a simple delivery network for static hypertexts. The legacy from these days can still be observed in the communication protocol used by increasingly sophisticated clients and applications. This thesis identifies the actual security requirements of modern web applications and shows that HTTP does not fit them: user and application authentication, message integrity and confidentiality, control-flow integrity, and application-to-application authorization. We explore the other protocols in the web stack and work out why they can not fill the gap. Our analysis shows that the underlying problem is the connectionless property of HTTP. However, history shows that a fresh start with web communication is far from realistic. As a consequence, we come up with approaches that contribute to meet the identified requirements. We first present impersonation attack vectors that begin before the actual user authentication, i.e. when secure web interaction and authentication seem to be unnecessary. Session fixation attacks exploit a responsibility mismatch between the web developer and the used web application framework. We describe and compare three countermeasures on different implementation levels: on the source code level, on the framework level, and on the network level as a reverse proxy. Then, we explain how the authentication credentials that are transmitted for the user login, i.e. the password, and for session tracking, i.e. the session cookie, can be complemented by browser-stored and user-based secrets respectively. This way, an attacker can not hijack user accounts only by phishing the user's password because an additional browser-based secret is required for login. Also, the class of well-known session hijacking attacks is mitigated because a secret only known by the user must be provided in order to perform critical actions. In the next step, we explore alternative approaches to static authentication credentials. Our approach implements a trusted UI and a mutually authenticated session using signatures as a means to authenticate requests. This way, it establishes a trusted path between the user and the web application without exchanging reusable authentication credentials. As a downside, this approach requires support on the client side and on the server side in order to provide maximum protection. Another approach avoids client-side support but can not implement a trusted UI and is thus susceptible to phishing and clickjacking attacks. Our approaches described so far increase the security level of all web communication at all time. This is why we investigate adaptive security policies that fit the actual risk instead of permanently restricting all kinds of communication including non-critical requests. We develop a smart browser extension that detects when the user is authenticated on a website meaning that she can be impersonated because all requests carry her identity proof. Uncritical communication, however, is released from restrictions to enable all intended web features. Finally, we focus on attacks targeting a web application's control-flow integrity. We explain them thoroughly, check whether current web application frameworks provide means for protection, and implement two approaches to protect web applications: The first approach is an extension for a web application framework and provides protection based on its configuration by checking all requests for policy conformity. The second approach generates its own policies ad hoc based on the observed web traffic and assuming that regular users only click on links and buttons and fill forms but do not craft requests to protected resources.}, subject = {Computersicherheit}, language = {en} } @phdthesis{Tran2015, author = {Tran, Nguyen Khanh Linh}, title = {Kaehler Differential Algebras for 0-Dimensional Schemes and Applications}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-3290}, school = {Universit{\"a}t Passau}, pages = {158}, year = {2015}, abstract = {The aim of this dissertation is to investigate Kaehler differential algebras and their Hilbert functions for 0-dimensional schemes in P^n. First we give relations between Kaehler differential 1-forms of fat point schemes and another fat point schemes. Then we determine the Hilbert polynomial and give a sharp bound for the regularity index of the module of Kaehler differential m-forms, for 05\%) better results than all other publicly available disambiguation algorithms on 7 of 9 datasets without data set specific tuning. Moreover, we discuss the influence of the quality of the knowledge base on the disambiguation accuracy and indicate that our algorithm achieves better results than non-publicly available state-of-the-art algorithms.}, language = {en} } @phdthesis{Alshawish2021, author = {Alshawish, Ali}, title = {Risk-based Security Management in Critical Infrastructure Organizations}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10026}, school = {Universit{\"a}t Passau}, pages = {xii, 181 Seiten}, year = {2021}, abstract = {Critical infrastructure and contemporary business organizations are experiencing an ongoing paradigm shift of business towards more collaboration and agility. On the one hand, this shift seeks to enhance business efficiency, coordinate large-scale distribution operations, and manage complex supply chains. But, on the other hand, it makes traditional security practices such as firewalls and other perimeter defenses insufficient. Therefore, concerns over risks like terrorism, crime, and business revenue loss increasingly impose the need for enhancing and managing security within the boundaries of these systems so that unwanted incidents (e.g., potential intrusions) can still be detected with higher probabilities. To this end, critical infrastructure organizations step up their efforts to investigate new possibilities for actively engaging in situational awareness practices to ensure a high level of persistent monitoring as well as on-site observation. Compliance with security standards is necessary to ensure that organizations meet regulatory requirements mostly shaped by a set of best practices. Nevertheless, it does not necessarily result in a coherent security strategy that considers the different aims and practical constraints of each organization. In this regard, there is an increasingly growing demand for risk-based security management approaches that enable critical infrastructures to focus their efforts on mitigating the risks to which they are exposed. Broadly speaking, security management involves the identification, assessment, and evaluation of long-term (or overall) objectives and interests as well as the means of achieving them. Due to the critical role of such systems, their decision-makers tend to enhance the system resilience against very unpleasant outcomes and severe consequences. That is, they seek to avoid decision options associated with likely extreme risks in the first place. Practically speaking, this risk attitude can significantly influence the decision-making process in such critical organizations. Towards incorporating the aversion to extreme risks into security management decisions, this thesis investigates thoroughly the capabilities of a recently emerged theory of games with payoffs that are probability distributions. Unlike traditional optimization techniques, this theory provides an alternative decision technique that is more robust to extreme risks and uncertainty. Furthermore, this thesis proposes a new method that gives a decision maker more control over the decision-making process through defining loss regions with different importance levels according to people's risk attitudes. In this way, the static decision analysis used in the distribution-valued games is transformed into a dynamic process to adapt to different subjective risk attitudes or account for future changes in the decision caused by a learning process or other changes in the context. Throughout their different parts, this thesis shows how theoretical models, simulation, and risk assessment models can be combined into practical solutions. In this context, it deals with three facets of security management: allocating limited security resources, prioritizing security actions, and tweaking decision making. Finally, the author discusses experiences and limitations distilled from this research and from investigating the new theory of games, which can be taken into account in future approaches.}, subject = {Spieltheorie}, language = {en} } @phdthesis{Silva2022, author = {Silva, Vivian dos Santos}, title = {A Composite Syntactic-Semantic Interpretable Text Entailment Approach Exploring Commonsense Knowledge Graphs}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10706}, school = {Universit{\"a}t Passau}, pages = {xiv, 229 Seiten}, year = {2022}, abstract = {Natural Language Processing has an important role in Artificial Intelligence for easing human-machine interaction. Processing human language, though, poses many challenges, among which is the semantics-related phenomenon known as language variability, the fact that the same thing can be said in several ways. NLP applications' inputs and outputs can be expressed in different forms, whose equivalence can be verified through inference. The textual entailment paradigm was established to enable the creation of a unifying framework for applied inference, providing a means of delivering other NLP task from handling inference issues in an ad-hoc manner, using instead the outputs of an inference-dedicated mechanism. Text entailment, the task of determining whether a piece of text logically follows from another piece of text, involves different scenarios, which can range from a simple syntactic variation to more complex semantic relationships between sentences. However, most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. The commonsense world knowledge necessary to support more complex inferences is also usually employed in a limited way, with most approaches sticking to shallow semantic information, leaving more elaborate semantic relationships aside. Furthermore, most systems still work as a "black box", providing a yes/no answer that does not explain the underlying reasoning process. This thesis aims at addressing these issues by proposing a composite interpretable approach for recognizing text entailment where the entailment pair is analyzed so the most relevant phenomenon is detected and the suitable method can be used to solve it. Syntactic variations are dealt with through the analysis of the sentences' syntactic structures, and semantic relationships are detected with the aid of a knowledge graph built from natural language dictionary definitions. Also, if a semantic matching is involved, the answer is made interpretable through the generation of natural language justifications that explain the semantic relationship between the pieces of text. The result is the XTE - Explainable Text Entailment - a system that outperforms well-established tools based on single-technique entailment algorithms, and that also gives an important step towards Explainable AI, allowing the inference model interpretation, making the semantic reasoning process explicit and understandable.}, language = {en} } @phdthesis{Opris2022, author = {Opris, Andre}, title = {Holomorphic Extensions in the Structure R_{an,exp}}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10691}, school = {Universit{\"a}t Passau}, pages = {233 Seiten}, year = {2022}, abstract = {In this thesis we consider real analytic functions, i.e. functions which can be described locally as convergent power series and ask the following: Which real analytic functions definable in R_{an,exp} have a holomorphic extension which is again definable in R_{an,exp}? Finding a holomorphic extension is of course not difficult simply by power series expansion. The difficulty is to construct it in a definably way. We will not answer the question above completely, but introduce a large non trivial class of definable functions in R_{an,exp} where for example functions which are iterated compositions from either side of globally subanalytic functions and the global logarithm are contained. We call them restricted log-exp-analytic. After giving some preliminary results like preparation theorems and Tamm's Theorem for this class of functions we are able to show that real analytic restricted log-exp-analytic functions have a holomorphic extension which is again restricted log-exp-analytic.}, subject = {O-Minimalit{\"a}t}, language = {en} } @phdthesis{Schmid2022, author = {Schmid, Josef}, title = {Learning-Based Quality of Service Prediction in Cellular Vehicle Communication}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10772}, school = {Universit{\"a}t Passau}, pages = {xvi, 147 Seiten}, year = {2022}, abstract = {Network communication has become a part of everyday life, and the interconnection among devices and people will increase even more in the future. A new area where this development is on the rise is the field of connected vehicles. It is especially useful for automated vehicles in order to connect the vehicles with other road users or cloud services. In particular for the latter it is beneficial to establish a mobile network connection, as it is already widely used and no additional infrastructure is needed. With the use of network communication, certain requirements come along. One of them is the reliability of the connection. Certain Quality of Service (QoS) parameters need to be met. In case of degraded QoS, according to the SAE level specification, a downgrade of the automated system can be required, which may lead to a takeover maneuver, in which control is returned back to the driver. Since such a handover takes time, prediction is necessary to forecast the network quality for the next few seconds. Prediction of QoS parameters, especially in terms of Throughput (TP) and Latency (LA), is still a challenging task, as the wireless transmission properties of a moving mobile network connection are undergoing fluctuation. In this thesis, a new approach for prediction Network Quality Parameters (NQPs) on Transmission Control Protocol (TCP) level is presented. It combines the knowledge of the environment with the low level parameters of the mobile network. The aim of this work is to perform a comprehensive study of various models including both Location Smoothing (LS) grid maps and Learning Based (LB) regression ones. Moreover, the possibility of using the location independence of a model as well as suitability for automated driving is evaluated.}, language = {en} } @phdthesis{Niklaus2022, author = {Niklaus, Christina}, title = {From Complex Sentences to a Formal Semantic Representation using Syntactic Text Simplification and Open Information Extraction}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10540}, school = {Universit{\"a}t Passau}, pages = {xxi, 301 Seiten}, year = {2022}, abstract = {Sentences that present a complex linguistic structure act as a major stumbling block for Natural Language Processing (NLP) applications whose predictive quality deteriorates with sentence length and complexity. The task of Text Simplification (TS) may remedy this situation. It aims to modify sentences in order to make them easier to process, using a set of rewriting operations, such as reordering, deletion or splitting. These transformations are executed with the objective of converting the input into a simplified output, while preserving its main idea and keeping it grammatically sound. State-of-the-art syntactic TS approaches suffer from two major drawbacks: first, they follow a very conservative approach in that they tend to retain the input rather than transforming it, and second, they ignore the cohesive nature of texts, where context spread across clauses or sentences is needed to infer the true meaning of a statement. To address these problems, we present a discourse-aware TS framework that is able to split and rephrase complex English sentences within the semantic context in which they occur. By generating a fine-grained output with a simple canonical structure that is easy to analyze by downstream applications, we tackle the first issue. For this purpose, we decompose a source sentence into smaller units by using a linguistically grounded transformation stage. The result is a set of selfcontained propositions, with each of them presenting a minimal semantic unit. To address the second concern, we suggest not only to split the input into isolated sentences, but to also incorporate the semantic context in the form of hierarchical structures and semantic relationships between the split propositions. In that way, we generate a semantic hierarchy of minimal propositions that benefits downstream Open Information Extraction (IE) tasks. To function well, the TS approach that we propose requires syntactically well-formed input sentences. It targets generalpurpose texts in English, such as newswire or Wikipedia articles, which commonly contain a high proportion of complex assertions. In a second step, we present a method that allows state-of-the-art Open IE systems to leverage the semantic hierarchy of simplified sentences created by our discourseaware TS approach in constructing a lightweight semantic representation of complex assertions in the form of semantically typed predicate-argument structures. In that way, important contextual information of the extracted relations is preserved that allows for a proper interpretation of the output. Thus, we address the problem of extracting incomplete, uninformative or incoherent relational tuples that is commonly to be observed in existing Open IE approaches. Moreover, assuming that shorter sentences with a more regular structure are easier to process, the extraction of relational tuples is facilitated, leading to a higher coverage and accuracy of the extracted relations when operating on the simplified sentences. Aside from taking advantage of the semantic hierarchy of minimal propositions in existing Open IE Abstract approaches, we also develop an Open IE reference system, Graphene. It implements a relation extraction pattern upon the simplified sentences. The framework we propose is evaluated within our reference TS implementation DisSim. In a comparative analysis, we demonstrate that our approach outperforms the state of the art in structural TS both in an automatic and a manual analysis. It obtains the highest score on three simplification datasets from two different domains with regard to SAMSA (0.67, 0.57, 0.54), a recently proposed metric targeted at automatically measuring the syntactic complexity of sentences which highly correlates with human judgments on structural simplicity and grammaticality. These findings are supported by the ratings from the human evaluation, which indicate that our baseline implementation DisSim returns fine-grained simplified sentences that achieve a high level of syntactic correctness and largely preserve the meaning of the input. Furthermore, a comparative analysis with the annotations contained in the RST Discourse Treebank (RST-DT) reveals that we are able to capture the contextual hierarchy between the split sentences with a precision of approximately 90\% and reach an average precision of almost 70\% for the classification of the rhetorical relations that hold between them. Finally, an extrinsic evaluation shows that when applying our TS framework as a pre-processing step, the performance of state-ofthe-art Open IE systems can be improved by up to 32\% in precision and 30\% in recall of the extracted relational tuples. Accordingly, we can conclude that our proposed discourse-aware TS approach succeeds in transforming sentences that present a complex linguistic structure into a sequence of simplified sentences that are to a large extent grammatically correct, represent atomic semantic units and preserve the meaning of the input. Moreover, the evaluation provides sufficient evidence that our framework is able to establish a semantic hierarchy between the split sentences, generating a fine-grained representation of complex assertions in the form of hierarchically ordered and semantically interconnected propositions. Finally, we demonstrate that state-of-the-art Open IE systems benefit from using our TS approach as a pre-processing step by increasing both the accuracy and coverage of the extracted relational tuples for the majority of the Open IE approaches under consideration. In addition, we outline that the semantic hierarchy of simplified sentences can be leveraged to enrich the output of existing Open IE systems with additional meta information, thus transforming the shallow semantic representation of state-of-the-art approaches into a canonical context-preserving representation of relational tuples.}, language = {en} } @phdthesis{Mandarawi2022, author = {Mandarawi, Waseem}, title = {Multi-objective Network Virtualization and its Applicability to Industrial Networks}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10606}, school = {Universit{\"a}t Passau}, pages = {xv, 156 Seiten}, year = {2022}, abstract = {Network virtualization provides high flexibility for deploying communication services in dense and heterogeneous environments. Two main approaches (dimensions) that are usually combined exist: Network Function Virtualization (NFV) technologies for functionality virtualization and Virtual Network Embedding (VNE) algorithms for resource virtualization. These approaches can be applied to different network levels, such as factory and enterprise levels of industrial networks. Several objectives and constraints, that might be conflicting, shall be considered when network virtualization is applied, mainly in complex topologies. This thesis proposes a network virtualization model that considers both virtualization dimensions, two network levels, and different objectives and constraints. The network levels considered are two primary levels in industrial networks. However, this consideration does not restrict the model to a particular environment or certain levels. The considered objectivities/constraints are topology, reliability, security, performance, and resource usage. Based on this model, we first build an overall combined solution for autonomic and composite virtual networking. This solution considers both virtualization dimensions, two network levels, and target objectives. Furthermore, this solution combines three novel virtualization sub-approaches that consider performance, reliability, and performance. However, the sub-approaches apply to different combinations of levels and dimensions, and the reliability approach additionally considers the resource usage objective. After presenting all solutions, we map them to the defined model. Regarding applicability to industrial networks, the combined approach is applied to an enterprise-level Industrial Internet of Things (IIoT) use case inspired by the smart factory concept in Industry 4.0. However, the sub-approaches are applied to more specific use cases. The performance and reliability solutions are integrated with relevant components of the Time Sensitive Networks (TSN) standard as a modern technology for industrial networks. The goal is to enrich the reliability and performance capabilities of TSN with the flexibility of network virtualization. In the combined approach, we compose and embed an environment-aware Extended Virtual Network (EVN) that represents the physical devices, virtual application functions, and required Service Function Chains (SFCs). We use the graph transformation method to transform abstract application requirements (represented by an Application Request (AR)) into an EVN. Both EVN composition and embedding methods consider the Substrate Network (SN) topology and different security, reliability, performance, and resource usage policies. These policies are applied with a certain priority and depend on the properties of communicating entities such as location and type. The EVN is embedded using property-based node mapping, reliability-aware branching, and a greedy chain embedding heuristic. The chain embedding heuristic is evaluated using a random topology that represents the use case. The performance sub-approach is NFV-based and is applied to a specific use case with Time-critical Traffic (TCT) flows. We develop and evaluate a complete framework for virtualizing Time-aware Shaper (TAS) using high-performance NFV. The reliability sub-approach is VNE-based and is applied to a specific factory level use case. We develop minimal and maximal branching heuristics based on a reliability-aware k-shortest path algorithm and compare them using a typical factory topology. We then integrate these algorithms with a Frame Replication and Elimination for Reliability (FRER) simulator to realize reliability policies by the autonomic and efficient configuration of a supporting technology. The security sub-approaches are related to both virtualization dimensions and are applied to generic enterprise-level use cases. However, the applicability of the security aspect to industrial networks is only shown in the combined (EVN) approach and its use case. We research the autonomic security management in Network Function Virtualization Infrastructure (NFVI) with the main goal of early reaction to threats through SFC reconfiguration through Virtual Network Function (VNF) live migration. This goal is approached by supporting the security measurements with a decision making architecture that considers, on the one hand, the threats and events in the environment and, on the other hand, the Service Level Agreement (SLA) between the NFVI provider and user. For this purpose, we classify the VNF-specific attacks and define possible early detectable behavior patterns. Finally, we develop a security-aware VNE heuristic that considers the security requirements of the Virtual Network (VN) and the security capabilities of the SN. This approach is modified in the combined approach to consider deploying virtualized security VNFs.}, language = {en} } @phdthesis{Alyousef2021, author = {Alyousef, Ammar}, title = {E-Mobility Management: Towards a Grid-friendly Smart Charging Solution}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9302}, school = {Universit{\"a}t Passau}, pages = {xvii, 159 Seiten}, year = {2021}, abstract = {Replacing fossil-fueled vehicles with Electric Vehicles (EVs) poses new challenges for power distribution networks. Specifically speaking, the electrification of the mobility sector relies on the ability to process and analyze information on when, where, for how long, or how fast charging processes will take place. Nevertheless, such kind of information is typically difficult to acquire or insufficiently predictable due to the dynamic nature of the system. Also, the increasing adoption rate of the renewable energy sources, specifically the domestic Photovoltaic (PV) systems, and the potentially associated grid defection scenarios will significantly impact the cost and efforts required to operate the grid in terms of power quality and demand-supply aspects. However, such emerging requirements have arguably not been taken into account when the distribution grid was built originally. Besides, expanding the distribution and transmission capacity is a very costly and lengthy process. Therefore, any proposed solution should be cost-effective as well as environment-, grid- and user-friendly. To this end, the advancements in Information and Communications Technology (ICT) are increasingly adopted and applied. This thesis addresses the rapidly growing EV sector and deals with the problems to overcome potential power quality degradation caused by the challenges mentioned above. Since time switch and radio ripple control as existing solutions in Germany are costly and neither very effective nor scalable as it requires hardware retrofitting of existing public Charging Stations (CSs), the primary focus of this work is the development of an appropriate, standards-based, scalable, and smart charging solution of EVs. Such a solution can, in turn, boost the usage of renewable energy by ensuring that the existing grid infrastructure can operate within its permissible limits while maintaining acceptable levels of power quality. This work introduces a new definition of the concept, "grid-friendly EV charging", where the power demand of a CS is adjusted depending on the real-time status of a power grid. In this regard, the conflicting concerns of stakeholders in an EV ecosystem are considered. For example, a Distribution System Operator (DSO) does not want to reveal a lot of technical details about the power grid or its status. Similarly, a Charging Service Provider (CSP) wants to keep its clients happy without sharing the details of its business model with others, namely, DSOs. For that sake, a distributed smart charging architecture is proposed in this thesis. It is event-driven and responds in nearly real-time to unforeseen and critical grid situations such as high/low voltage, congestion, phase unbalance, and harmonics. In that regard, the publish/subscribe messaging pattern, used as a part of the architecture, enables an efficient and well-performing communication scheme among the different components. Moreover, an indication mechanism about the different issues in a power grid is developed; it adopts the traffic light model. It works as a black box to separate smart controllers for each CS and configured only by the CSP. Smart chargers enable a smooth adjustment of the charging power to avoid drastic changes in the grid state. To that end, two types of intelligent controllers are developed and tested. While the first controller is inspired by the fuzzy logic, the second one is inspired by the slow-start mechanism used in TCP to control congestion in computer networks. A simulative approach is applied to evaluate the solution, thereby, a topology of a real low voltage grid with realistic load and generation profiles is used. Furthermore, a set of metrics is defined regarding the main concerns of stakeholders: voltage, overloading, fairness, the satisfaction of EV users and grid operator, as well as the grid-friendly behavior of a CS/ EV user. The evaluation shows that the solution is able to guarantee a safe operation of the grid. The proposed system can ensure a grid-friendly charging by sacrificing of a small portion of user satisfaction, that sacrifice of a user is awarded via a points-based reward system. Last but not least, the proposed distributed controllers are compared to two other controllers: (1) a decentralized controller based only on sensing the local voltage and (2) a very strict centralized controller focusing on grid-friendliness. The latter ensures proportional fairness among users regarding the objective function of the optimization problem solved in each simulation step. The distributed controllers are superior to the decentralized controller in terms of grid friendly and fairness and converge in general to the centralized one.}, subject = {Elektromobilit{\"a}t}, language = {en} } @phdthesis{Niedermeier2020, author = {Niedermeier, Florian}, title = {Power-Adaptive Computing in Future Energy Networks}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9993}, school = {Universit{\"a}t Passau}, pages = {xvi, 204 Seiten}, year = {2020}, abstract = {The current electricity grid is undergoing major changes. There is increasing pressure to move away from power generation from fossil fuels, both due to ecological concerns and fear of dependencies on scarce natural resources. Increasing the share of decentralized generation from renewable sources is a widely accepted way to a more sustainable power infrastructure. However, this comes at the price of new challenges: generation from solar or wind power is not controllable and only forecastable with limited accuracy. To compensate for the increasing volatility in power generation, exerting control on the demand side is a promising approach. By providing flexibility on demand side, imbalances between power generation and demand may be mitigated. This work is concerned with developing methods to provide grid support on demand side while limiting the associated costs. This is done in four major steps: first, the target power curve to follow is derived taking both goals of a grid authority and costs of the respective load into account. In the following, the special case of data centers as an instance of significant loads inside a power grid are focused on more closely. Data center services are adapted in a way such as to achieve the previously derived power curve. By means of hardware power demand models, the required adaptation of hardware utilization can be derived. The possibilities of adapting software services are investigated for the special use case of live video encoding. A method to minimize quality of experience loss while reducing power demand is presented. Finally, the possibility of applying probabilistic model checking to a continuous demand-response scenario is demonstrated.}, subject = {Energieversorgung}, language = {en} } @phdthesis{Ansah2021, author = {Ansah, Frimpong}, title = {Performance and optimization technologies for software defined industrial networks}, publisher = {Universit{\"a}t Passau}, address = {Passau}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9002}, school = {Universit{\"a}t Passau}, pages = {xxi, 173 Seiten}, year = {2021}, abstract = {The concept of programmable networks is radically changing the way communication infrastructures are designed, integrated, and operated. Currently, the topic is spearheaded by concepts such as software-defined networking, forwarding and control element separation, and network function virtualization. Notably, software-defined networking has attracted significant attention in telecommunication and data centers and thus already in some production-grade networks. Despite the prevalence of software-defined networking in these domains, industrial networks are yet to see its benefits to encourage adoption. However, the misconceptions around the concept itself, the role of virtualization, and algorithms pose a significant obstacle. Furthermore, the desire to accommodate new services in the automation industry results in a pattern of constantly increasing complexity of industrial networks, which is compounded by the requirement to provide stringent deterministic service guarantees considering characteristically different applications and thus posing a significant challenge for management, configuration, and maintenance as existing solutions are architecturally inflexible. Therefore, the first contribution of this thesis addresses the misconceptions around software-defined networking by providing a comparative analysis of programmable network concepts, detailing where software-defined networks compare with other concepts and how its principles can be leveraged to evolve industrial networks. Armed with the fundamental principles of programmable networks, the second contribution identifies virtualization technologies and proposes novel algorithms to provide varied quality of service guarantees on converged time-sensitive Ethernet networks using software-defined networking concepts. Finally, a performance analysis of a software-defined hybrid deployment solution for control and management of time-sensitive Ethernet networks that integrates proposed novel algorithms is presented as an industrial use-case that enables industrial operators to harness the full potential of time-sensitive networks.}, language = {en} } @phdthesis{Lang2021, author = {Lang, Thomas}, title = {AI-Supported Interactive Segmentation of 3D Volumes}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9221}, school = {Universit{\"a}t Passau}, pages = {184 Seiten}, year = {2021}, abstract = {The segmentation of volumetric datasets, i.e., the partitioning of the data into disjoint sub-volumes with the goal to extract information about these regions,is a difficult problem and has been discussed in medical imaging for decades. Due to the ever-increasing imaging capabilities, in particular in X-ray computed tomography (CT) or magnetic resonance imaging, segmentation in industrial applications also gains interest. Especially in industrial applications the generated datasets increase in size. Hence, most applications apply well-known techniques in a 2+1-dimensional manner,i.e., they apply image segmentation procedures on each slice separately and track the progress along the axis of the volume in which the slices are stacked on. This discards the information on preceding or subsequent slices, which is often assumed to be nearly identical. However, in the industrial context this might prove wrong since industrial parts might change their appearance significantly over the course of even a few slices. Moreover, artifacts can further distort the content of the slices. Therefore, three-dimensional processing of voxel volumes has to be preferred, which induces constraints upon the segmentation procedures. For example, they must not consider global information as it is usually not feasible in big scans to compute them efficiently. Yet another frequent problem is that applications focus on individual parts only and algorithms are tailored to that case. Most prominent medical segmentation procedures do so by applying methods to specifically find the liver and only the liver of a patient, for example. The implication is that the same method then cannot be applied to find other parts of the scan and such methods have to be designed individually for any object to be segmented. Flexible segmentation methods are needed too specifically when partitioning unique scans. We define a unique scan to be a voxel dataset for which no comparable volume exists. Classical examples include the use case of cultural heritage where not only the objects themselves are unique but also scan parameters are optimized to obtain the best image quality possible for that specific scan. This thesis aims at introducing novel methods for voxelwise classifications based on local geometric features. The latter are computed from local environments around each voxel and extract information in similar ways as humans do, namely by observing their similarity to geometric or textural primitives. These features serve as the foundation to learning the proposed voxelwise classifiers and to discriminate between segmented and unsegmented voxels. On the one hand, they perform fully automated clustering of volumes for which a representative random sample is extracted first. On the other hand, a set of segmenting classifiers can be trained from few seed voxels, i.e., volume elements for which a domain expert marked if they belong to the components that shall be segmented. The interactive selection offers the advantage that no completely labeled voxel volumes are necessary and hence that unique scans of objects can be segmented for which no comparable scans exist. Overall, it will be shown that all proposed segmentation methods are effectively of linear runtime with respect to the number of voxels in the volume. Thus, voxel volumes without size restrictions can be segmented in an efficient linear pass through the volume. Finally, the segmentation performance is evaluated on selected datasets which shows that the introduced methods can achieve good results on scans from a broad variety of domains for both small and big voxel volumes.}, language = {en} } @phdthesis{SalehiRizi2021, author = {Salehi Rizi, Fatemeh}, title = {Graph Representation Learning for Social Networks}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9211}, school = {Universit{\"a}t Passau}, pages = {ix, 130 Seiten}, year = {2021}, abstract = {Online social networks provide a rich source of information about millions of users worldwide. However, due to sparsity and complex structure, analyzing these networks is quite challenging and expensive. Recently, graph embedding emerged to map networked data into low-dimensional representations, i.e. vector embeddings. These representations are fed into off-the-shelf machine learning algorithms to simplify and speed up graph analytic tasks. Given the immense importance of social network analysis, in this thesis, we aim to study graph embedding for social networks in three directions. Firstly, we focus on social networks at microscopic level to primarily encode the structural characteristic of users' personal networks so-called ego networks. These representations are utilized in evaluation tasks whose performance depends on relational information from direct neighbors. For example, social circle prediction and event attendance inference both need structural information from neighbors in social networks. Secondly, we explore assessing the content of vector embeddings in terms of topological properties. This could be explained via two proposed approaches: 1) a learning to rank algorithm in which the model weights reveal the importance of properties at subgraph level (ego networks), 2) a regression model for direct approximation of network statistical properties at vertex level. Thirdly, we propose extensions of graph embedding to capture sign or additional content of social networks. Users in social media often express their feelings and attitudes towards others which forms sentiment links besides social links. We design a joint objective function whose terms capture semantics of both social and sentiment links simultaneously. We also propose a multi-task learning framework for networks with attributes and labels by stacking autoencoders. The weights of the learning tasks are automatically assigned via an adaptive loss weighting layer.}, language = {en} } @article{Basmadjian2019, author = {Basmadjian, Robert}, title = {Flexibility-Based Energy and Demand Management in Data Centers}, series = {Energies}, volume = {2019}, journal = {Energies}, number = {12}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/en12173301}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-9251}, pages = {1 -- 22}, year = {2019}, abstract = {The power demand (kW) and energy consumption (kWh) of data centers were augmenteddrastically due to the increased communication and computation needs of IT services. Leveragingdemand and energy management within data centers is a necessity. Thanks to the automated ICTinfrastructure empowered by the IoT technology, such types of management are becoming more feasiblethan ever. In this paper, we look at management from two different perspectives: (1) minimization of theoverall energy consumption and (2) reduction of peak power demand during demand-response periods.Both perspectives have a positive impact on total cost of ownership for data centers. We exhaustivelyreviewed the potential mechanisms in data centers that provided flexibilities together with flexiblecontracts such as green service level and supply-demand agreements. We extended state-of-the-artby introducing the methodological building blocks and foundations of management systems for theabove mentioned two perspectives. We validated our results by conducting experiments on a lab-gradescale cloud computing data center at the premises of HPE in Milano. The obtained results support thetheoretical model, by highlighting the excellent potential of flexible service level agreements in Green IT:33\% of overall energy savings and 50\% of power demand reduction during demand-response periods inthe case of data center federation.}, language = {en} } @phdthesis{Schmid2021, author = {Schmid, Matthias}, title = {Towards Storing 3D Model Graphs in Relational Databases}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-10353}, school = {Universit{\"a}t Passau}, pages = {243 Seiten}, year = {2021}, abstract = {The increasing relevance of massive graph data reinforces the need for adequate graph data management. While several graph database engines have been developed, the storage of graph data in a relational database management system, and therefore the seamless integration into existing information systems remains an open challenge. Motivated by the use case to integrate Building Information Modeling (BIM) data into the MonArch system, we propose a solution that transforms the BIM data into a property graph and stores this graph in the database system. We present a novel approach to efficiently store property graph data in a relational database management system using JSON functionality and redundant storage of edges in adjacency lists and show how to import huge data sets into this schema. Applying this approach, we import data sets of up to nearly 1 TB of disk space within the relational database, while only having 96 GB of main memory available. We also present a new approach of how to retrieve data from this database schema, translating queries written in the popular property graph query language Cypher into SQL. Hence, we provide an intuitive way to write semantically complex queries. We also demonstrate the efficiency of our approach using the standardized Linked Data Benchmark Council - Social Network Benchmark (LDBC - SNB) framework. Our approach increases the throughput for this benchmark by up to 85 times, compared to existing approaches for RDBMS. In addition, we propose a new method to transform BIM data into the property graph model and how to apply the aforementioned property graph storage to this data. We can import IFC models of up to 300 MB within five minutes. We show the suitability of our approach using our own use case specific benchmark, which we integrated into the previously mentioned Social Network Benchmark. For our interactive use case-specific queries, we achieve response times faster than 5 ms in 99\% of all executions. Finally, we present how the aforementioned approach to store BIM data in a relational database management system is integrated into the existing MonArch system by splitting the different functionalities of our approach into a microservice architecture.}, language = {en} } @phdthesis{Bermeitinger2024, author = {Bermeitinger, Bernhard}, title = {Investigating a Second-Order Optimization Strategy for Neural Networks}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14087}, school = {Universit{\"a}t Passau}, pages = {xv, 59 Seiten}, year = {2024}, abstract = {In summary, this cumulative dissertation investigates the application of the conjugate gradient method CG for the optimization of artificial neural networks (NNs) and compares this method with common first-order optimization methods, especially the stochastic gradient descent (SGD). The presented research results show that CG can effectively optimize both small and very large networks. However, the default machine precision of 32 bits can lead to problems. The best results are only achieved in 64-bits computations. The research also emphasizes the importance of the initialization of the NNs' trainable parameters and shows that an initialization using singular value decomposition (SVD) leads to drastically lower error values. Surprisingly, shallow but wide NNs, both in Transformer and CNN architectures, often perform better than their deeper counterparts. Overall, the research results recommend a re-evaluation of the previous preference for extremely deep NNs and emphasize the potential of CG as an optimization method.}, language = {en} } @article{FrankBoettgerMexisetal.2023, author = {Frank, Florian and B{\"o}ttger, Simon and Mexis, Nico and Anagnostopoulos, Nikolaos Athanasios and Mohamed, Ali and Hartmann, Martin and Kuhn, Harald and Helke, Christian and Arul, Tolga and Katzenbeisser, Stefan and Hermann, Sascha}, title = {CNT-PUFs: highly robust and heat-tolerant carbon-nanotube-based physical unclonable functions}, volume = {2023}, number = {13(22)}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/nano13222930}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14011}, pages = {24 Seiten}, year = {2023}, abstract = {In this work, we explored a highly robust and unique Physical Unclonable Function (PUF) based on the stochastic assembly of single-walled Carbon NanoTubes (CNTs) integrated within a wafer-level technology. Our work demonstrated that the proposed CNT-based PUFs are exceptionally robust with an average fractional intra-device Hamming distance well below 0.01 both at room temperature and under varying temperatures in the range from 23 °C to 120 °C. We attributed the excellent heat tolerance to comparatively low activation energies of less than 40 meV extracted from an Arrhenius plot. As the number of unstable bits in the examined implementation is extremely low, our devices allow for a lightweight and simple error correction, just by selecting stable cells, thereby diminishing the need for complex error correction. Through a significant number of tests, we demonstrated the capability of novel nanomaterial devices to serve as highly efficient hardware security primitives.}, language = {en} } @phdthesis{Fink2023, author = {Fink, Simon Dominik}, title = {Constrained Planarity Algorithms in Theory and Practice}, doi = {10.15475/cpatp.2024}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13817}, school = {Universit{\"a}t Passau}, pages = {216 Seiten}, year = {2023}, abstract = {In the constrained planarity setting, we ask whether a graph admits a crossing-free drawing that additionally satisfies a given set of constraints. These constraints are often derived from very natural problems; prominent examples are Level Planarity, where vertices have to lie on given horizontal lines indicating a hierarchy, Partially Embedded Planarity, where we extend a given drawing without modifying already-drawn parts, and Clustered Planarity, where we additionally draw the boundaries of clusters which recursively group the vertices in a crossing-free manner. In the last years, the family of constrained planarity problems received a lot of attention in the field of graph drawing. Efficient algorithms were discovered for many of them, while a few others turned out to be NP-complete. In contrast to the extensive theoretical considerations and the direct motivation by applications, only very few of the found algorithms have been implemented and evaluated in practice. The goal of this thesis is to advance the research on both theoretical as well as practical aspects of constrained planarity. On the theoretical side, we consider two types of constrained planarity problems. The first type are problems that individually constrain the rotations of vertices, that is they restrict the counter-clockwise cyclic orders of the edges incident to vertices. We give a simple linear-time algorithm for the problem Partially Embedded Planarity, which also generalizes to further constrained planarity variants of this type. The second type of constrained planarity problem concerns more involved planarity variants that come down to the question whether there are embeddings of one or multiple graphs such that the rotations of certain vertices are in sync in a certain way. Clustered Planarity and a variant of the Simultaneous Embedding with Fixed Edges Problem (Connected SEFE-2) are well-known problems of this type. Both are generalized by our Synchronized Planarity problem, for which we give a quadratic algorithm. Through reductions from various other problems, we provide a unified modelling framework for almost all known efficiently solvable constrained planarity variants that also directly provides a quadratic-time solution to all of them. For both our algorithms, a key ingredient for reaching an efficient solution is the usage of the right data structure for the problem at hand. In this case, these data structures are the SPQR-tree and the PC-tree, which describe planar embedding possibilities from a global and a local perspective, respectively. More specifically, PC-trees can be used to locally describe the possible cyclic orders of edges around vertices in all planar embeddings of a graph. This makes it a key component for our algorithms, as it allows us to test planarity while also respecting further constraints, and to communicate constraints arising from the surrounding graph structure between vertices with synchronized rotation. Bridging over to the practical side, we present the first correct implementation of PC-trees. We also describe further improvements, which allow us to outperform all implementations of alternative data structures (out of which we only found very few to be fully correct) by at least a factor of 4. We show that this yields a simple and competitive planarity test that can also yield an embedding to certify planarity. We also use our PC-tree implementation to implement our quadratic algorithm for solving Synchronized Planarity. Here, we show that our algorithm greatly outperforms previous attempts at solving related problems like Clustered Planarity in practice. We also engineer its running time and show how degrees of freedom in the theoretical algorithm can be leveraged to yield an up to tenfold speed-up in practice.}, language = {en} } @techreport{EckhardtFreilingHerrmannetal.2023, author = {Eckhardt, Dennis and Freiling, Felix and Herrmann, Dominik and Katzenbeisser, Stefan and P{\"o}hls, Henrich C.}, title = {Sicherheit in der Digitalisierung des Alltags: Definition eines ethnografisch-informatischen Forschungsfeldes f{\"u}r die L{\"o}sung allt{\"a}glicher Sicherheitsprobleme}, doi = {10.15475/sidial.2023}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13721}, pages = {18 Seiten}, year = {2023}, abstract = {In den vergangenen Jahrzehnten hat es un{\"u}bersehbar zahlreiche Fortschritte im Bereich der IT-Sicherheitsforschung gegeben, etwa in den Bereichen Systemsicherheit und Kryptographie. Es ist jedoch genauso un{\"u}bersehbar, dass IT-Sicherheitsprobleme im Alltag der Menschen fortbestehen. Mutmaßlich liegt dies an der Komplexit{\"a}t von Alltagssituationen, in denen Sicherheitsmechanismen und Ger{\"a}tefunktionalit{\"a}t sowie deren Heterogenit{\"a}t in schwer antizipierbarer Weise mit menschlichem Verst{\"a}ndnis und Alltagsgebrauch interagieren. Um die wissenschaftliche Forschung besser auf Menschen und deren IT-Sicherheitsbed{\"u}rfnisse auszurichten, m{\"u}ssen wir daher den Alltag der Menschen besser verstehen. Das Verst{\"a}ndnis von Alltag ist in der Informatik jedoch noch unterentwickelt. Dieser Beitrag m{\"o}chte das Forschungsfeld "Sicherheit in der Digitalisierung des Alltags" definieren, um Forschenden die Gelegenheit zu geben, ihre Anstrengungen in diesem Bereich zu b{\"u}ndeln. Wir machen dabei Vorschl{\"a}ge einerseits zur inhaltlichen Eingrenzung der informatischen Forschung. Andererseits m{\"o}chten wir durch die Einbeziehung von Forschungsmethoden aus der Ethnografie, die Erkenntnisse aus der durchaus subjektiven Beobachtung des "Alltags" vieler einzelner Individuen zieht, zur methodischen Weiterentwicklung interdisziplin{\"a}rer Forschung in diesem Feld beitragen. Die IT- Sicherheitsforschung kann dann Bestehendes gezielt f{\"u}r eine richtige Alltagstauglichkeit optimieren und neue grundlegende Sicherheitsfunktionalit{\"a}ten f{\"u}r die konkreten Herausforderungen im Alltag entwickeln.}, language = {de} } @phdthesis{Danner2023, author = {Danner, Dominik}, title = {Towards Quality of Service and Fairness in Smart Grid Applications}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13731}, school = {Universit{\"a}t Passau}, pages = {xx, 172 Seiten}, year = {2023}, abstract = {Due to the increasing amount of distributed renewable energy generation and the emerging high demand at consumer connection points, e. g., electric vehicles, the power distribution grid will reach its capacity limit at peak load times if it is not expensively enhanced. Alternatively, smart flexibility management that controls user assets can help to better utilize the existing power grid infrastructure for example by sharing available grid capacity among connected electric vehicles or by disaggregating flexibility requests to hybrid photovoltaic battery energy storage systems in households. Besides maintaining an acceptable state of the power distribution grid, these smart grid applications also need to ensure a certain quality of service and provide fairness between the individual participants, both of which are not extensively discussed in the literature. This thesis investigates two smart grid applications, namely electric vehicle charging-as-a-service and flexibility-provision-as-a-service from distributed energy storage systems in private households. The electric vehicle charging service allocation is modeled with distributed queuing-based allocation mechanisms which are compared to new probabilistic algorithms. Both integrate user constraints (arrival time, departure time, and energy required) to manage the quality of service and fairness. In the queuing-based allocation mechanisms, electric vehicle charging requests are packetized into logical charging current packets, representing the smallest controllable size of the charging process. These packets are queued at hierarchically distributed schedulers, which allocate the available charging capacity using the time and frequency division multiplexing technique known from the networking domain. This allows multiple electric vehicles to be charged simultaneously with variable charging currents. To achieve high quality of service and fairness among electric vehicle charging processes, dynamic weights are introduced into a weighted fair queuing scheduler that considers electric vehicle departure time and required energy for prioritization. The distributed probabilistic algorithms are inspired by medium access protocols from computer networking, such as binary exponential backoff, and control the quality of service and fairness by adjusting sampling windows and waiting periods based on user requirements. The second smart grid application under investigation aims to provide flexibility provision-as-a-service that disaggregates power flexibility requests to distributed battery energy storage systems in private households. Commonly, the main purpose of stationary energy storage is to store energy from a local photovoltaic system for later use, e. g., for overnight charging of an electric vehicle. This is optimized locally by a home energy management system, which also allows the scheduling of external flexibility requests defined by the deviation from the optimal power profile at the grid connection point, for example, to perform peak shaving at the transformer. This thesis discusses a linear heuristic and a meta heuristic to disaggregate a flexibility request to the single participating energy management systems that are grouped into a flexibility pool. Thereby, the linear heuristic iteratively assigns portions of the power flexibility to the most appropriate energy management system for one time slot after another, minimizing the total flexibility cost or maximizing the probability of flexibility delivery. In addition, a multi-objective genetic algorithm is proposed that also takes into account power grid aspects, quality of service, and fairness among par-ticipating households. The genetic operators are tailored to the flexibility disaggregation search space, taking into account flexibility and energy management system constraints, and enable power-optimized buffering of fitness values. Both smart grid applications are validated on a realistic power distribution grid with real driving patterns and energy profiles for photovoltaic generation and household consumption. The results of all proposed algorithms are analyzed with respect to a set of newly defined metrics on quality of service, fairness, efficiency, and utilization of the power distribution grid. One of the main findings is that none of the tested algorithms outperforms the others in all quality of service metrics, however, integration of user expectations improves the service quality compared to simpler approaches. Furthermore, smart grid control that incorporates users and their flexibility allows the integration of high-load applications such as electric vehicle charging and flexibility aggregation from distributed energy storage systems into the existing electricity distribution infrastructure. However, there is a trade-off between power grid aspects, e. g., grid losses and voltage values, and the quality of service provided. Whenever active user interaction is required, means of controlling the quality of service of users' smart grid applications are necessary to ensure user satisfaction with the services provided.}, language = {en} } @phdthesis{Brummer2022, author = {Brummer, Stephan}, title = {Numerisch robuste Berechnung der zirkul{\"a}ren Sichtbarkeitsmenge}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-12299}, school = {Universit{\"a}t Passau}, pages = {viii, 170 Seiten}, year = {2022}, abstract = {Sichtbarkeitsprobleme, wie das Folgende, geh{\"o}ren zu den grundlegenden Problemen der algorithmischen Geometrie: Berechne zu einem einfachen Polygon, dem sogenannten Kanal, und zu einem darin enthaltenen Punkt die von diesem Punkt aus sichtbare Punktmenge. Dabei ist ein Punkt von einem anderen Punkt aus sichtbar, wenn deren Verbindungsstrecke den Kanal nicht verl{\"a}sst. Wir wollen uns in dieser Arbeit mit zirkul{\"a}rer Sichtbarkeit besch{\"a}ftigen. Zur Verbindung zweier Punkte sind dann nicht nur Strecken, sondern auch Kreisb{\"o}gen zul{\"a}ssig. Außerdem betrachten wir als Ausgangspunkt dieser sogenannten Sichtbarkeitskreisb{\"o}gen und -strecken eine Kante des Kanals anstatt eines einzelnen Punkts. Konkret liefert diese Arbeit einen Beitrag zur numerisch robusten Bestimmung der zirkul{\"a}ren Sichtbarkeitsmenge ausgehend von einer Kante des Kanals. Hierf{\"u}r wird in dieser Arbeit ein Algorithmus vorgestellt, mit dem f{\"u}r einen gegebenen Punkt festgestellt werden kann, ob dieser von der Startkante aus sichtbar ist. Im Fall eines sichtbaren Punkts wird ein Sichtbarkeitskreisbogen berechnet, der zwei Kanalber{\"u}hrungen besitzt. Damit kann der Algorithmus bei geeigneter Wahl des zu untersuchenden Punkts - der als dritte Kanalber{\"u}hrung fungiert - direkt zur Berechnung von sogenannten Grenzkreisb{\"o}gen der Sichtbarkeitsmenge benutzt werden. Diese definieren den Rand der zirkul{\"a}ren Sichtbarkeitsmenge und zeichnen sich dadurch aus, dass sie vom Kanal dreimal abwechselnd von links und von rechts ber{\"u}hrt werden. Der beschriebene Algorithmus basiert auf der Untersuchung derjenigen Kreisb{\"o}gen, die zwar nicht notwendigerweise vollst{\"a}ndig im Kanal liegen, aber die Startkante mit dem Punkt verbinden, dessen Sichtbarkeit bestimmt werden soll. Insbesondere werden dabei die Bereiche untersucht, in denen der jeweilige Kreisbogen den Kanal verl{\"a}sst, die sogenannten Verletzungen. Da die „Schwere" einer solchen Verletzung quantifizierbar ist, wird ein iteratives Vorgehen erm{\"o}glicht. Dabei wird der Kreisbogen iterativ so ver{\"a}ndert, dass dieser bei gleichem Endpunkt den Kanal immer „weniger verl{\"a}sst". Ist der Endpunkt und damit der zu untersuchende Punkt nicht sichtbar, wird im Laufe des Algorithmus festgestellt, dass keine derartige Verbesserung m{\"o}glich ist. Der vorgestellte Algorithmus ist numerisch robust, einfach umzusetzen und besitzt eine in der Anzahl der Kanalecken lineare Laufzeit.}, language = {de} } @article{HerboldHautli‑JaniszHeueretal., author = {Herbold, Steffen and Hautli‑Janisz, Annette and Heuer, Ute and Kikteva, Zlata and Trautsch, Alexander}, title = {A large‑scale comparison of human‑written versus ChatGPT‑generated essays}, series = {Scientific Reports}, volume = {13}, journal = {Scientific Reports}, publisher = {Springer Nature}, doi = {10.1038/s41598-023-45644-9}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13961}, pages = {11 Seiten}, abstract = {ChatGPT and similar generative AI models have attracted hundreds of millions of users and have become part of the public discourse. Many believe that such models will disrupt society and lead to significant changes in the education system and information generation. So far, this belief is based on either colloquial evidence or benchmarks from the owners of the models—both lack scientific rigor. We systematically assess the quality of AI-generated content through a large-scale study comparing human-written versus ChatGPT-generated argumentative student essays. We use essays that were rated by a large number of human experts (teachers). We augment the analysis by considering a set of linguistic characteristics of the generated essays. Our results demonstrate that ChatGPT generates essays that are rated higher regarding quality than human-written essays. The writing style of the AI models exhibits linguistic characteristics that are different from those of the human-written essays. Since the technology is readily available, we believe that educators must act immediately. We must re-invent homework and develop teaching concepts that utilize these AI models in the same way as math utilizes the calculator: teach the general concepts first and then use AI tools to free up time for other learning objectives.}, language = {en} } @article{HassenBenAhmed, author = {Hassen, Wiem Fekih and Ben Ahmed, Mariem}, title = {Optimization of a Redox-Flow Battery Simulation Model Based on a Deep Reinforcement Learning Approach}, series = {Batteries}, volume = {10}, journal = {Batteries}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/batteries10010008}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13994}, pages = {20 Seiten}, abstract = {Vanadium redox-flow batteries (VRFBs) have played a significant role in hybrid energy storage systems (HESSs) over the last few decades owing to their unique characteristics and advantages. Hence, the accurate estimation of the VRFB model holds significant importance in large-scale storage applications, as they are indispensable for incorporating the distinctive features of energy storage systems and control algorithms within embedded energy architectures. In this work, we propose a novel approach that combines model-based and data-driven techniques to predict battery state variables, i.e., the state of charge (SoC), voltage, and current. Our proposal leverages enhanced deep reinforcement learning techniques, specifically deep q-learning (DQN), by combining q-learning with neural networks to optimize the VRFB-specific parameters, ensuring a robust fit between the real and simulated data. Our proposed method outperforms the existing approach in voltage prediction. Subsequently, we enhance the proposed approach by incorporating a second deep RL algorithm—dueling DQN—which is an improvement of DQN, resulting in a 10\% improvement in the results, especially in terms of voltage prediction. The proposed approach results in an accurate VFRB model that can be generalized to several types of redox-flow batteries.}, language = {en} } @article{HassenImenAzzouz, author = {Hassen, Wiem Fekih and Imen Azzouz, Imen Azzouz}, title = {Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach}, series = {Energies}, volume = {16}, journal = {Energies}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/en16248102}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-13985}, pages = {18 Seiten}, abstract = {The worldwide adoption of Electric Vehicles (EVs) has embraced promising advancements toward a sustainable transportation system. However, the effective charging scheduling of EVs is not a trivial task due to the increase in the load demand in the Charging Stations (CSs) and the fluctuation of electricity prices. Moreover, other issues that raise concern among EV drivers are the long waiting time and the inability to charge the battery to the desired State of Charge (SOC). In order to alleviate the range of anxiety of users, we perform a Deep Reinforcement Learning (DRL) approach that provides the optimal charging time slots for EV based on the Photovoltaic power prices, the current EV SOC, the charging connector type, and the history of load demand profiles collected in different locations. Our implemented approach maximizes the EV profit while giving a margin of liberty to the EV drivers to select the preferred CS and the best charging time (i.e., morning, afternoon, evening, or night). The results analysis proves the effectiveness of the DRL model in minimizing the charging costs of the EV up to 60\%, providing a full charging experience to the EV with a lower waiting time of less than or equal to 30 min.}, language = {en} } @article{PatilGhasemideMeer2024, author = {Patil, Amit and Ghasemi, Abdorasoul and de Meer, Hermann}, title = {Analysis of protection blinding in active distribution grids}, series = {IET Renewable Power Generation}, journal = {IET Renewable Power Generation}, doi = {10.1049/rpg2.13037}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14661}, pages = {15 Seiten}, year = {2024}, abstract = {Protection blinding is a challenging issue in renewables-penetrated distribution grids and refers to a situation where a circuit breaker may not trip due to fault current contribution from distributed generation. This research addresses how the distributed generation location and capacity impact the operation of the circuit breaker in terms of the response time of the circuit breakers. The relative electrical distances of the faults and distributed generation to the circuit breakers are considered. The impact of distributed generation capacity considering the fault location is characterized using a new index called the heterogeneity index. The electrical distance between distributed generations and circuit breakers and the electrical distance between fault and circuit breaker is considered by a second new index called the electrical distance ratio. Data analysis on simulation results shows that these indices capture the phenomena of protection blinding caused by distributed generation. Results show that a higher distributed generation penetration and faults that are electri cally further away from a circuit breaker show severe cases of protection blinding captured by the indices. Furthermore, it is demonstrated how these indices can identify the worst impacted locations in the distribution grid. A key result is that protection blinding does not necessarily occur solely due to the presence of distributed generation between a circuit breaker and a fault, but is dependent on factors such as distributed generation location in the distribution grid, fault level, fault level distribution across the generation units and fault location.}, language = {en} } @phdthesis{Puellen2024, author = {P{\"u}llen, Dominik}, title = {Holistic Security Engineering for Software-Defined Vehicles}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14497}, school = {Universit{\"a}t Passau}, pages = {XXIII, 161 Seiten}, year = {2024}, abstract = {With the increasing use of digital technologies in the automotive sector, the traditional automobile is undergoing a structural transformation, requiring new technologies and enabling innovative mobility concepts. In particular, the ability to drive automatically or even fully autonomously, update control software, and remain connected to the environment allows attackers to infiltrate highly critical vehicle systems and take control without adequate protection. Once not only individual vehicles but entire fleets are dominated by software, cyberattacks could disrupt a significant portion of the infrastructure and expose passengers to substantial risks. This work follows a holistic approach to protecting highly automated software-defined vehicles from cyberattacks by designing and implementing security concepts in the main phases of a vehicle's lifecycle. We use SAE level 4 prototype vehicles to evaluate our proposed techniques. We start with a systematic security requirement analysis using the ISA-62443 standard series, demonstrating how threats can be identified in a collaborative, hierarchical process and how the resulting security risks impact the software and hardware architecture of a self-driving vehicle. We show how this analysis process results in concrete requirements whose consideration reduces the overall security risk to a tolerable level. Subsequently, we develop technical solutions for selected requirements. We begin by securing the CAN and FlexRay legacy protocols, which we foresee being used in specific areas of SDV in a transitional period despite technological changes. To enable vehicle-wide security management, we address the management and distribution of cryptographic keys within such networks, mainly focusing on resource-constrained devices. We propose using lightweight implicit certificates for deriving cryptographic group keys that can be used in CAN networks. Additionally, we demonstrate how the slot-based frame structure of the FlexRay protocol allows for efficient "multi-slot" authentication, for which we calculate cryptographic keys using hash-based key chains. SDV use Ethernet-based communication protocols and custom middleware stacks to transmit large amounts of data in real-time. We develop a three-stage security process for the novel ASOA, which enables the development and central orchestration of system-agnostic functional software components on embedded systems and HPC platforms. After the central specification of the security architecture at the data flow level, security tokens are automatically calculated and distributed for runtime protection of the service-oriented, DDS-based data transmission. Our process ensures the strict separation of function and system knowledge, allowing for cost-effective and adaptable security architecture management. The evaluation in four self-driving, software-defined vehicles demonstrates an average runtime overhead of approximately 5.71\%. As the initial risk analysis and actual cyberattacks have shown, protective measures against the compromise of control units must be taken alongside communication security. To address this, we develop a method for verifying and validating the software integrity of control units. A governmental third party confirms a measurement through a digital certificate, proving the examined vehicle's trustworthiness and suitability for participation in automated traffic. In the final step of this work, we present an assessment scheme that allows software-defined vehicles to evaluate security incidents during operation in terms of their maximum expected damage and initiate appropriate countermeasures. We follow the ISO/SAE 21434 standard and model attack paths using a graph representing dependencies among internal vehicle assets to account for the propagation effects of cyberattacks. The assessment of a security incident considers not only the probability of individual attack paths but also the vehicle context. Our practical evaluation demonstrates that we can detect, report, and assess security incidents below the human reaction time in the earlier mentioned prototype vehicles.}, language = {en} } @phdthesis{Alhamzeh2023, author = {Alhamzeh, Alaa}, title = {Language Reasoning by means of Argument Mining and Argument Quality}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-12699}, school = {Universit{\"a}t Passau}, pages = {ix, 154 Seiten}, year = {2023}, abstract = {Understanding of financial data has always been a point of interest for market participants to make better informed decisions. Recently, different cutting edge technologies have been addressed in the Financial Technology (FinTech) domain, including numeracy understanding, opinion mining and financial ocument processing. In this thesis, we are interested in analyzing the arguments of financial experts with the goal of supporting investment decisions. Although various business studies confirm the crucial role of argumentation in financial communications, no work has addressed this problem as a computational argumentation task. In other words, the automatic analysis of arguments. In this regard, this thesis presents contributions in the three essential axes of theory, data, and evaluation to fill the gap between argument mining and financial text. First, we propose a method for determining the structure of the arguments stated by company representatives during the public announcement of their quarterly results and future estimations through earnings conference calls. The proposed scheme is derived from argumentation theory at the micro-structure level of discourse. We further conducted the corresponding annotation study and published the first financial dataset annotated with arguments: FinArg. Moreover, we investigate the question of evaluating the quality of arguments in this financial genre of text. To tackle this challenge, we suggest using two levels of quality metrics, considering both the Natural Language Processing (NLP) literature of argument quality assessment and the financial era peculiarities. Hence, we have also enriched the FinArg data with our quality dimensions to produce the FinArgQuality dataset. In terms of evaluation, we validate the principle of ensemble learning on the argument identification and argument unit classification tasks. We show that combining a traditional machine learning model along with a deep learning one, via an integration model (stacking), improves the overall performance, especially in small dataset settings. In addition, despite the fact that argument mining is mainly a domain dependent task, to this date, the number of studies that tackle the generalization of argument mining models is still relatively small. Therefore, using our stacking approach and in comparison to the transfer learning model of DistilBert, we address and analyze three real-world scenarios concerning the model robustness over completely unseen domains and unseen topics. Furthermore, with the aim of the automatic assessment of argument strength, we have investigated and compared different (refined) versions of Bert-based models that incorporate external knowledge in the decision layer. Consequently, our method outperforms the baseline model by 13 ± 2\% in terms of F1-score through integrating Bert with encoded categorical features. Beyond our theoretical and methodological proposals, our model of argument quality assessment, annotated corpora, and evaluation approaches are publicly available, and can serve as strong baselines for future work in both FinNLP and computational argumentation domains. Hence, directly exploiting this thesis, we proposed to the community, a new task/challenge related to the analysis of financial arguments: FinArg-1, within the framework of the NTCIR-17 conference. We also used our proposals to react to the Touch{\´e} challenge at the CLEF 2021 conference. Our contribution was selected among the «Best of Labs».}, language = {en} } @phdthesis{Grassl2024, author = {Graßl, Isabella}, title = {Diversity in Programming Education: Effects of Topic and Group Constellation on Young Programming Novices}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15049}, school = {Universit{\"a}t Passau}, pages = {xi, 256 Seiten}, year = {2024}, abstract = {The field of software engineering faces a significant diversity crisis, characterized by a critical lack of heterogeneity despite ongoing efforts to promote gender equality. The persistent male dominance in this domain has created an urgent need for more heterogeneous groups in software engineering. This lack of diversity not only hinders underrepresented groups from entering the field but also prevents them from gaining initial programming experiences, which are a core component of software engineering and essential for developing computational thinking. To address this crisis and its implications, early interventions are key in shaping positive perceptions, building confidence, and sparking initial interest in programming among underrepresented groups before societal stereotypes of programming as a nerdy field manifests. This means starting with basic programming courses for children and continuing through to first-year university students in order to foster technical skills and computational thinking, alongside creativity and collaboration. However, there is limited understanding of how introductory programming course designs impact diversity-dependent characteristics to create welcoming and learning-friendly environments. This understanding is particularly important for underrepresented groups, especially girls, to benefit from their first programming experiences as they are often hindered by the initial perception of programming as (1) abstract and unappealing, and (2) non-social to novices. Engaging, creative, and relatable topics in programming courses might demystify complex programming concepts, making them more accessible, less intimidating, and appealing. However, understanding programming is not just about the content---it is also about the context in which it is learned. Introducing programming as social activity is important, particularly for young learners. By emphasizing team work, we might encourage collaboration and peer support, counteracting the lone-wolf programmer stereotype. Therefore, this doctoral thesis investigates the effects of both key aspects in programming courses---(1) topic choices and (2) group constellations---on young programming novices. The aim is to provide a holistic understanding of how different course designs can support diverse learners and promote gender equality in programming education. While this research primarily addresses gender diversity due to the persistent gender gap in software engineering, it also examines additional diversity dimensions, including age, ethnicity, prior programming experience, disabilities, and educational background. A total of 13 studies were conducted within this thesis, examining the current state of educational settings and utilizing various introductory programming courses designed for children aged 8 to 18, as well as first-year university students. These studies employed different programming environments, such as Scratch and Sonic Pi, and incorporated a variety of topics and group constellations to observe their effects on student outcomes. By using a mixed-methods design, data were gathered through surveys, observations, and both data-driven and manual code analysis. Key findings reveal that it is particularly noteworthy how children utilize the programming environment to engage with and creatively express topics aligned with their interests which also align mostly with gender-stereotypes, including elements from internet and popular culture as well as socio-cultural narratives. However, gender-sensitive and neutral topic choices enhance engagement, self-efficacy, contribution, code quality and creative output, while also contributing to reduce stereotypical beliefs about programming, particularly among girls. In line with the findings for the course topic, group constellations also influence programming experiences. In particular, introducing pair programming in courses shows a promising approach for young learners, but attention must be paid to mitigate socially learned gender-stereotypical behaviours. Another finding indicates that, unlike professional software teams, mixed-diverse student teams often encounter substantial challenges, thus benefit from clear communication guidelines and supportive environments to promote better collaboration. This doctoral thesis concludes with guidelines for designing more effective and inclusive introductory programming courses. These recommendations include using gender-sensitive course materials, allowing for creative freedom through topic choices while encouraging the use of advanced programming concepts, promoting collaboration through pair programming while fostering enhanced communication, boosting self-efficacy with quick positive feedback for girls in particular, and providing emotional support for underrepresented groups. By following these guidelines, educators can create more engaging, inclusive, and effective programming courses. This may ultimately promote a more equitable and diverse future generation of professional software developers while also fostering computational thinking, encouraging a broader interest in programming among all young learners.}, subject = {Softwareentwicklung}, language = {en} } @phdthesis{Berger2024, author = {Berger, Christian}, title = {Towards Fast and Adaptive Byzantine State Machine Replication for Planetary-Scale Systems}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15059}, school = {Universit{\"a}t Passau}, pages = {ix, 181 Seiten}, year = {2024}, abstract = {State machine replication (SMR) is a classical approach for building resilient distributed systems. In Byzantine fault-tolerant (BFT) systems, no concrete assumptions are made about the behavior of faulty replicas. With the advancement of distributed ledger technologies (DLT), planetary-scale BFT SMR ist becoming practical and necessary as it can serve as a consensus primitive to keep the ledger consistent. In our view, the alignment of BFT SMR to DLT brings new challenges, for instance the scalability aspect, where recent research works less frequently address latency improvements than throughput improvements. Further challenges include the geographic dispersion of replicas within a planetary-scale system and the need of a BFT SMR protocol to react to environmental changes during runtime. This thesis has the objective to improve BFT SMR for planetary-scale systems by lowering the protocol latency observed by clients and by making the BFT SMR system adaptive, i.e., enabling replicas to react to perceived changes such as changing network characteristics or faulty replicas. As a first contribution of this thesis, we discover that fast, consensus-free (read-only) operations is a flawed optimization in seminal BFT SMR frameworks, such as PBFT and BFT-SMaRt. We explain how the read-only optimization can violate the protocol's liveness by showing an attack and then present a solution that makes the overall, optimized protocol both live and linearizable. The second contribution is Adaptive Wide-Area Replication (AWARE), which enables a geo-replicated system to adapt to its environment, thus improving the geographical scalability of consensus if replicas are dispersed across the world. Essentially, AWARE is an automated and dynamic voting-weight tuning and leader positioning scheme, which supports the emergence of fast consensus quorums in the system and builds upon previous work, the WHEAT protocol. AWARE combines reliable self-monitoring with a consensus latency prediction model, thus striving to minimize the system's consensus latency at runtime, which subsequently results in latency improvements observed by clients scattered across the globe, which we validate through experiments. The third contribution presents FlashConsensus, a protocol derived from AWARE, that also adjusts the resilience threshold. The core idea is the tentative use of a lower resilience threshold which leads to smaller consensus quorums and thus consensus acceleration in common-case scenarios where we expect only few faulty replicas. FlashConsensus achieves threat-level awareness through the incorporation of two modes of operation and BFT forensic support and guarantees liveness and linearizability under optimal resilience. Moreover, FlashConsensus allows for client-side speculation by using incremental consistency guarantees to further lower request latency. Additionally, we investigate on the question whether we can reason about the performance of large-scale systems utilizing simulations. We discover, that we can faithfully forecast the performance of BFT protocols by plugging real protocol implementations into a high-performance network simulator. For instance, simulation results reveal that, using 51 replicas scattered across the planet, FlashConsensus can finalize operations in less than 0.4 s, which is half of the time required for a PBFT-like protocol in the same network, and matching the latency of this protocol running on the best possible internet links (transmitting at 67\% of the speed of light).}, language = {en} } @phdthesis{Sentanoe2024, author = {Sentanoe, Stewart}, title = {VMIaaS: Virtual Machine Introspection as a Service}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15027}, school = {Universit{\"a}t Passau}, pages = {vi, 121 Seiten}, year = {2024}, abstract = {In this digital era, communication in the digital world is becoming part of our daily lives. One key technology that becomes part of this digital transformation is cloud computing. It allows users to have a running system as a virtual machine (VM) on the cloud without owning a physical server. Unfortunately, adversaries can also use those systems to conduct criminal activities. Therefore, developing a method to extract evidence from those systems is also necessary. One way is through digital forensics, and one method to do digital forensics of a VM is using virtual machine introspection (VMI). However, VMI has yet to be made available by any public cloud provider. This thesis addresses this issue by introducing methods for deploying VMI on public cloud providers. Four main challenges have to be solved. Firstly, VMI requires access to the hypervisor, which practically can access all VMs running on the same server. This leads to security and privacy issues where customers can introspect each other VMs. To solve this problem, this thesis introduces KVMIveggur, a versatile access control of VMI. It comes with different options that every customer can choose from based on their needs. Secondly, VMI introduces overhead to the running VM. This is because most of the introspection mechanisms perform data access to the monitored VM. Performing data access on a running VM can cause data inconsistency. Hence, pausing the VM before executing the data access is better. However, when the VM pausing frequency is high, it will affect the performance of the monitored VM. The current state-of-the-art techniques use caching to reduce the VM pausing frequency. However, it faces a problem: the cached data may be outdated compared to the actual data. Therefore, this thesis introduces VMIFresh, a better caching mechanism. We leverage both active and passive tracing mechanisms to ensure high performance and consistency of the data (freshness). Thirdly, many state-of-the-art VMI libraries and applications run perfectly only on Intel processors because Intel CPUs provide the best hardware support for VMI. However, AMD and ARM processors are getting more popular in cloud computing. Thus, it is necessary to retrofit VMI capabilities to support AMD and ARM processors. This thesis describes the requirements to employ VMI on AMD and ARM processors. We also provide the implementation of those requirements. Finally, to do introspection using VMI, it is crucial to have proper symbol information (layout and location of data structures) of the introspected operating system (OS) and user applications. While many existing VMI approaches concentrate primarily on analyzing OS data structures, analyzing user application data often receives no attention. In our approach, we address this gap by focussing on application-level introspection. We have identified several use cases that require this kind of introspection. We focus on cryptographic key extraction for two specific instances: secure shell (SSH) and transport layer security (TLS) by leveraging the power of machine learning techniques to locate those keys in the main memory effectively and efficiently. After we had solved those challenges, we combined a couple of our approaches and introduced two VMI applications: Sarracenia and VMIGuard. Sarracenia is a deception technology that tracks activities done on an SSH session. The main goal of Sarracenia is to attract adversaries away from the production system and learn about their behavior. On the other hand, VMIGuard also monitors the SSH traffic. But, it specifically monitors the activity of any git-related activities. The main goal of VMIGuard is to ensure the integrity of the hosted data from any internal malicious actor.}, subject = {Cloud Computing}, language = {en} } @article{DeinerFeldmeierFraseretal.2023, author = {Deiner, Adina and Feldmeier, Patric and Fraser, Gordon and Schweikl, Sebastian and Wang, Wengran}, title = {Automated test generation for SCRATCH programs}, series = {Empirical Software Engineering}, volume = {28}, journal = {Empirical Software Engineering}, number = {3}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10664-022-10255-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023091108301581209964}, pages = {1 -- 63}, year = {2023}, abstract = {The importance of programming education has led to dedicated educational program- ming environments, where users visually arrange block-based programming constructs that typically control graphical, interactive game-like programs. The SCRATCH programming environment is particularly popular, with more than 90 million registered users at the time of this writing. While the block-based nature of S CRATCH helps learners by preventing syntactical mistakes, there nevertheless remains a need to provide feedback and support in order to implement desired functionality. To support individual learning and classroom settings, this feedback and support should ideally be provided in an automated fashion, which requires tests to enable dynamic program analysis. In prior work we introduced W HISKER , a framework that enables automated testing of S CRATCH programs. However, creating these automated tests for S CRATCH programs is challenging. In this paper, we therefore investigate how to automatically generate W HISKER tests. Generating tests for S CRATCH raises important challenges: First, game-like programs are typically randomised, leading to flaky tests. Second, S CRATCH programs usually consist of animations and interactions with long delays, inhibiting the application of classical test generation approaches. Thus, the new application domain raises the question of which test generation technique is best suited to produce high coverage tests capable of detecting faulty behaviour. We investigate these questions using an extension of the W HISKER test framework for automated test generation. Evaluation on common programming exercises, a random sample of 1000 S CRATCH user programs, and the 1000 most popular S CRATCH programs demonstrates that our approach enables W HISKER to reliably accelerate test executions, and even though many SCRATCH programs are small and easy to cover, there are many unique challenges for which advanced search-based test generation using many-objective algorithms is needed in order to achieve high coverage.}, language = {en} } @article{Schwartz2023, author = {Schwartz, Niels}, title = {Topology of closure systems in algebraic lattices}, series = {Algebra universalis}, volume = {84}, journal = {Algebra universalis}, number = {2}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00012-023-00815-7}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023090808111682406614}, pages = {1 -- 33}, year = {2023}, abstract = {Algebraic lattices are spectral spaces for the coarse lower topology. Closure systems in algebraic lattices are studied as subspaces. Connections between order theoretic properties of a closure system and topological properties of the subspace are explored. A closure system is algebraic if and only if it is a patch closed subset of the ambient algebraic lattice. Every subset X in an algebraic lattice P generates a closure system〈X〉P . The closure system〈Y 〉P generated by the patch closure Y of X is the patch closure of〈X〉P. If X is contained in the set of nontrivial prime elements of P then〈X〉P is a frame and is a coherent algebraic frame if X is patch closed in P. Conversely, if the algebraic lattice P is coherent then its set of nontrivial prime elements is patch closed.}, language = {en} } @article{MuenchRutterStumpf2023, author = {M{\"u}nch, Miriam and Rutter, Ignaz and Stumpf, Peter}, title = {Partial and Simultaneous Transitive Orientations via Modular Decompositions}, series = {Algorithmica}, volume = {86}, journal = {Algorithmica}, number = {4}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00453-023-01188-y}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024022914111908687000}, pages = {1263 -- 1292}, year = {2023}, abstract = {A natural generalization of the recognition problem for a geometric graph class is the problem of extending a representation of a subgraph to a representation of the whole graph. A related problem is to find representations for multiple input graphs that coin- cide on subgraphs shared by the input graphs. A common restriction is the sunflower case where the shared graph is the same for each pair of input graphs. These problems translate to the setting of comparability graphs where the representations correspond to transitive orientations of their edges. We use modular decompositions to improve the runtime for the orientation extension problem and the sunflower orientation problem to linear time. We apply these results to improve the runtime for the partial represen- tation problem and the sunflower case of the simultaneous representation problem for permutation graphs to linear time. We also give the first efficient algorithms for these problems on circular permutation graphs.}, language = {en} } @article{TrautschHerboldGrabowski2023, author = {Trautsch, Alexander and Herbold, Steffen and Grabowski, Jens}, title = {Are automated static analysis tools worth it? An investigation into relative warning density and external software quality on the example of Apache open source projects}, series = {Empirical Software Engineering}, volume = {28}, journal = {Empirical Software Engineering}, number = {3}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10664-023-10301-2}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023091108203018898026}, pages = {1 -- 21}, year = {2023}, abstract = {Automated Static Analysis Tools (ASATs) are part of software development best practices. ASATs are able to warn developers about potential problems in the code. On the one hand, ASATs are based on best practices so there should be a noticeable effect on software quality. On the other hand, ASATs suffer from false positive warnings, which developers have to inspect and then ignore or mark as invalid. In this article, we ask whether ASATs have a measurable impact on external software quality, using the example of PMD for Java. We investigate the relationship between ASAT warnings emitted by PMD on defects per change and per file. Our case study includes data for the history of each file as well as the differences between changed files and the project in which they are contained. We investigate whether files that induce a defect have more static analysis warnings than the rest of the project. Moreover, we investigate the impact of two different sets of ASAT rules. We find that, bug inducing files contain less static analysis warnings than other files of the project at that point in time. However, this can be explained by the overall decreasing warning density. When compared with all other changes, we find a statistically significant difference in one metric for all rules and two metrics for a subset of rules. However, the effect size is negligible in all cases, showing that the actual difference in warning density between bug inducing changes and other changes is small at best.}, language = {en} } @article{FruehwirthProchno2023, author = {Fr{\"u}hwirth, Lorenz and Prochno, Joscha}, title = {H{\"o}lder's inequality and its reverse — a probabilistic point of view}, series = {Mathematische Nachrichten}, volume = {296}, journal = {Mathematische Nachrichten}, number = {12}, publisher = {Wiley}, address = {Hoboken}, doi = {10.1002/mana.202200411}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023062315175042989607}, pages = {5493 -- 5512}, year = {2023}, abstract = {In this article, we take a probabilistic look at H{\"o}lder's inequality, considering the ratio of terms in the classical H{\"o}lder inequality for random vectors in ℝ𝑛. We prove a central limit theorem for this ratio, which then allows us to reverse the inequality up to a multiplicative constant with high probability. The models of randomness include the uniform distribution on 𝓁𝑛𝑝 balls and spheres. We also provide a Berry-Esseen-type result and prove a large and a moderate deviation principle for the suitably normalized H{\"o}lder ratio.}, language = {en} } @phdthesis{Hofstadler2024, author = {Hofstadler, Julian}, title = {Qualitative and quantitative convergence results for randomised integration methods}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15196}, school = {Universit{\"a}t Passau}, pages = {III, 80 Seiten}, year = {2024}, abstract = {In this thesis different randomised integration methods based on either, randomised Quasi-Monte Carlo, or (adaptive) Markov chain Monte Carlo methods are studied. Depending on the underlying integration problem we show qualitative and quantitative results, which ensure the asymptotic correctness of an algorithm or provide explicit error bounds. The first problem we consider is Lebesgue integration in the unit cube. We prove that a class of structured randomised integration methods is consistent w.r.t. convergence in mean and probability for any integrable function. Under slightly stronger integrability conditions we show that one also has almost sure convergence for median modified methods. We demonstrate the applicability of our theoretical results by considering randomly shifted lattice rules, randomised (t,d)-sequences, Latin hypercube samples, and randomised Frolov points. Secondly, we study integration w.r.t. probability measures which are available only via their non-normalised density. In this context we investigate Markov chain Monte Carlo methods which satisfy a spectral gap condition and functions which do not need to have a finite second moment. We prove error bounds for the absolute mean error where the rate of convergence is optimal. Illustrative scenarios where our theory is applicable are the random walk Metropolis algorithm as well as slice samplers. Finally, we study so-called adaptive increasingly rare Markov chain Monte Carlo algorithms. Based on a simultaneous Wasserstein contraction assumption we estimate the mean squared error and also prove bounds which characterise the path-wise convergence of the estimator. To demonstrate the applicability of our results we consider a number of examples, among which are doubly intractable distributions.}, language = {en} } @phdthesis{Greifenstein2024, author = {Greifenstein, Luisa}, title = {Supporting Primary School Programming Education through Formative Feedback}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15188}, school = {Universit{\"a}t Passau}, pages = {viii, 204 Seiten}, year = {2024}, abstract = {Children are increasingly surrounded by computer science aspects in their everyday life. Primary school education aims at empowering children to participate in and reflect on their environment. Therefore, computer science related contents such as programming are increasingly introduced into primary school curricula. However, this also involves challenges in particular for teachers, who need to familiarise themselves with the new curriculum. As a result, primary school teachers often struggle to help primary school children with their programming issues. Corrective feedback given during the learning process (i. e. formative feedback) can help by promoting cognitive factors such as content knowledge. This thesis therefore aims to support primary school programming education through formative feedback. In order to shed light on different perspectives, both teachers and children participated in the studies in a mixed methods design. Teachers' challenges and children's programming issues were explored as a basis for knowing what both target groups struggle with. This was done by conducting content analysis on the challenges and issues collected and using the resulting categories for further quantitative analysis. The effects of different characteristics of feedback on the effectiveness and efficiency of teaching and learning programming were then explained. This was done by asking the teachers and children to explain their ratings and conducting content analysis on their explanations. The support of primary school programming education through formative feedback builds on the major challenge of teachers' lack of content knowledge and the corresponding strategies of teacher training and automated feedback. Indeed, automated feedback was found to be mostly helpful for debugging and task creation. In order to provide direct support to children, common programming issues were identified in terms of the understanding of programming concepts and the usage of the programming environment. Effects on children's learning and their preferences were identified for several feedback characteristics, leading for example to elaborated hints instead of simple direct instructions. Based on these results, a formative feedback approach of hint cards was developed and evaluated. The hint cards approach proved to be a useful example strategy for supporting primary school programming education through formative feedback.}, subject = {R{\"u}ckmeldung}, language = {en} } @phdthesis{Welearegai2023, author = {Welearegai, Gebrehiwet Biyane}, title = {Precise Detection of Injection Attacks in Real-world Applications}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-12926}, school = {Universit{\"a}t Passau}, pages = {xvi, 120 Seiten}, year = {2023}, abstract = {Code injection attacks like the one used in the high-profile 2017 Equifax breach, have become increasingly common, ranking at the top of OWASP's list of critical web application vulnerabilities. The injection attacks can also target embedded applications running on processors like ARM and Xtensa by exploiting memory bugs and maliciously altering the program's behavior or even taking full control over a system. Especially, ARM's support of low power consumption without sacrificing performance is leading the industry to shift towards ARM processors, which advances the attention of injection attacks as well. In this thesis, we are considering web applications and embedded applications (running on ARM and Xtensa processors) as the target of injection attacks. To detect injection attacks in web applications, taint analysis is mostly proposed but the precision, scalability, and runtime overhead of the detection depend on the analysis types (e.g., static vs dynamic, sound vs unsound). Moreover, in the existing dynamic taint tracking approach for Java- based applications, even the most performant can impose a slowdown of at least 10-20\% and often far more. On the other hand, considering the embedded applications, while some initial research has tried to detect injection attacks (i.e., ROP and JOP) on ARM, they suffer from high performance or storage overhead. Besides, the Xtensa has been neglected though used in most firmware-based embedded WiFi home automation devices. This thesis aims to provide novel approaches to precisely detect injection attacks on both the web and embedded applications. To that end, we evaluate JavaScript static analysis frameworks to evaluate the security of a hybrid app (JS \& native) from an industrial partner, provide RIVULET - a tool that precisely detects injection attacks in Java-based real-world applications, and investigate injection attacks detection on ARM and Xtensa platforms using hardware performance counters (HPCs) and machine learning (ML) techniques. To evaluate the security of the hybrid application, we initially compare the precision, scalability, and code coverage of two widely-used static analysis frameworks—WALA and SAFE. The result of our comparison shows that SAFE provides higher precision and better code coverage at the cost of somewhat lower scalability. Based on these results, we analyze the data flows of the hybrid app via taint analysis by extending the SAFE's taint analysis and detected a potential for injection attacks of the hybrid application. Similarly, to detect injection attacks in Java-based applications, we provide Rivulet which monitors the execution of developer-written functional tests using dynamic taint tracking. Rivulet uses a white-box test generation technique to re-purpose those functional tests to check if any vulnerable flow could be exploited. We compared Rivulet to the state-of-the-art static vulnerability detector Julia on benchmarks and Rivulet outperformed Julia in both false positives and false negatives. We also used Rivulet to detect new vulnerabilities. Moreover, for applications running on ARM and Xtensa platforms, we investigate ROP1 attack detection by combining HPCs and ML techniques. We collect data exploiting real- world vulnerable applications and small benchmarks to train the ML. For ROP attack detection on ARM, we also implement an online monitor which labels a program's execution as benign or under attack and stops its execution once the latter is detected. Evaluating our ROP attack detection approach on ARM provides a detection accuracy of 92\% for the offline training and 75\% for the online monitoring. Similarly, our ROP attack detection on the firmware-only Xtensa processor provides an overall average detection accuracy of 79\%. Last but not least, this thesis shows how relevant taint analysis is to precisely detect injection attacks on web applications and the power of HPC combined with machine learning in the control flow injection attacks detection on ARM and Xtensa platforms.}, language = {en} } @article{GhoshDastidarJurgovskySiblinietal.2022, author = {Ghosh Dastidar, Kanishka and Jurgovsky, Johannes and Siblini, Wissam and Granitzer, Michael}, title = {NAG: neural feature aggregation framework for credit card fraud detection}, series = {Knowledge and Information Systems}, volume = {2022}, journal = {Knowledge and Information Systems}, number = {64}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10115-022-01653-0}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2022060219175235764329}, pages = {831 -- 858}, year = {2022}, abstract = {The state-of-the-art feature-engineering method for fraud classification of electronic pay-ments uses manually engineered feature aggregates, i.e., descriptive statistics of thetransaction history. However, this approach has limitations, primarily that of being dependenton expensive human expert knowledge. There have been attempts to replace manual aggre-gation through automatic feature extraction approaches. They, however, do not consider thespecific structure of the manual aggregates. In this paper, we define the novel Neural Aggre-gate Generator (NAG), a neural network-based feature extraction module that learns featureaggregates end-to-end on the fraud classification task. In contrast to other automatic featureextraction approaches, the network architecture of the NAG closely mimics the structureof feature aggregates. Furthermore, the NAG extends learnable aggregates over traditionalones through soft feature value matching and relative weighting of the importance of differ-ent feature constraints. We provide a proof to show the modeling capabilities of the NAG.We compare the performance of the NAG to the state-of-the-art approaches on a real-worlddataset with millions of transactions. More precisely, we show that features generated with theNAG lead to improved results over manual aggregates for fraud classification, thus demon-strating its viability to replace them. Moreover, we compare the NAG to other end-to-endapproaches such as the LSTM or a generic CNN. Here we also observe improved results. Weperform a robust evaluation of the NAG through a parameter budget study, an analysis of theimpact of different sequence lengths and also the predictions across days. Unlike the LSTMor the CNN, our approach also provides further interpretability through the inspection of itsparameters.}, language = {en} } @phdthesis{Patil2025, author = {Patil, Amit Dilip}, title = {Towards Resilient Protection of Interconnected ICT and Power Systems}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-16088}, school = {Universit{\"a}t Passau}, pages = {xxii, 173 Seiten}, year = {2025}, abstract = {Due to the increasing number of distributed renewable energy sources, the distribution grid faces new operational challenges. Information and Communication Technology (ICT) systems can resolve these challenges through grid services that use automation, monitoring, and real-time decision-making, helping maintain an acceptable operational state of the distribution grid. However, the reliance of the power system on the ICT system and vice versa in the so-called smart grid creates interdependencies between the systems, which present new pathways for failure propagation. Therefore, these interdependencies require special attention to ensure stable system operation in the face of these challenges. However, these interdependencies have not been studied extensively in the literature. This thesis investigates approaches to model, quantify and improve the performance and resilience of the smart grid infrastructure. The interdependencies are formalised as interconnectors, entities that exist in all the connected systems. These interconnectors consist of components from both systems, where the components are modelled as state variables. These state variables determine the interconnector state and the service delivered. Failures represented by a change in state variables may impact the state. These state variables are deployed in a discrete event simulation framework to determine the system performance over time. The simulation result is represented on a two-dimensional state-space diagram depicting the operational state and service delivered. This allows for the resilience analysis of a system under various scenarios. The interdependencies are further investigated by exploring the role of ICT-based grid services in power grids, whose state is defined based on ICT properties, such as latency. These properties are formalised using property graphs. The ICT properties obtained from these graphs are used to parameterise a finite state automaton model of a grid service states, which are then used to determine the state of the entire smart grid. Case studies of state estimation and adaptive protection highlight the application of this approach. The use of ICT in state estimation allows the distinction of a global and perceived view of the power grid, which influences decision-making in the face of challenges. This thesis further investigates the protection system in detail. The overcurrent protection system is adversely impacted by distributed generation, resulting in undesired phenomena such as protection blinding. This thesis characterises this phenomenon by proposing two indices that capture the protection trip time under the influence of distributed generation. These indices consider the electrical distance between faults, protection and distributed generation. These indices and simulation results identify the worst-impacted locations in the power grid in terms of protection trip time. They also identify fault locations under given assumptions that do not cause protection blinding. ICT can resolve protection blinding by adapting the sensitivity of protection relays. However, since faults must be cleared in a short timeframe, communication delays may adversely impact the fault-clearing time. A discrete event simulation model is proposed to study protection performance in distribution grids. Investigation of time distribution assumptions reveals that the lognormal distribution accurately captures the circuit breaker trip time. The impact of the distributed generation and communication delay on the protection system is determined by measuring fault-clearing times using discrete event simulation. Results show that for the system studied, protection blinding is critical for low impedance faults in grids with high fault levels, while high impedance faults are critical in grids with low fault levels. Moreover, sympathetic tripping is seen at increased distribution grid fault levels and fault impedance. Furthermore, while communication systems reduce fault clearing times, increased delays harm protection systems. Finally, communication system components like sensors can fail, preventing fault detection. This thesis proposes a genetic algorithm-based approach to optimally place redundant sensors, minimising protection blinding under communication uncertainty within a redundancy budget. Results demonstrate the algorithm's effectiveness in optimising redundant sensor locations, reducing system costs, and improving fault tolerance. For the system and scenarios investigated, an average of 60\% redundant sensors are relocated, reducing the average protection trip time by 36.65\% compared to a baseline approach that does not consider communication uncertainty. This encourages incorporating communication component failure considerations in power system planning.}, language = {en} } @article{FekihHassenChallouf2024, author = {Fekih Hassen, Wiem and Challouf, Maher}, title = {Long short-term renewable energy sources prediction for grid-management systems based on stacking ensemble model}, series = {Energies}, volume = {2024}, journal = {Energies}, number = {17(13)}, doi = {10.3390/en17133145}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14649}, pages = {19 Seiten}, year = {2024}, abstract = {The transition towards sustainable energy systems necessitates effective management of renewable energy sources alongside conventional grid infrastructure. This paper presents a comprehensive approach to optimizing grid management by integrating Photovoltaic (PV), wind, and grid energies to minimize costs and enhance sustainability. A key focus lies in developing an accurate scheduling algorithm utilizing Mixed Integer Programming (MIP), enabling dynamic allocation of energy resources to meet demand while minimizing reliance on cost-intensive grid energy. An ensemble learning technique, specifically a stacking algorithm, is employed to construct a robust forecasting pipeline for PV and wind energy generation. The forecasting model achieves remarkable accuracy with a Root Mean Squared Error (RMSE) of less than 0.1 for short-term (15 min and one day ahead) and long-term (one week and one month ahead) predictions. By combining optimization and forecasting methodologies, this research contributes to advancing grid management systems capable of harnessing renewable energy sources efficiently, thus facilitating cost savings and fostering sustainability in the energy sector.}, language = {en} } @article{Kaiser2023, author = {Kaiser, Tobias}, title = {Growth of log-analytic functions}, series = {Archiv der Mathematik}, volume = {120}, journal = {Archiv der Mathematik}, number = {6}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00013-023-01857-y}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023091614564557203657}, pages = {605 -- 614}, year = {2023}, abstract = {We show that unary log-analytic functions are polynomially bounded. In the higher dimensional case, globally a log-analytic function can have exponential growth. We show that a log-analytic function is polynomially bounded on a definable set which contains the germ of every ray at infinity.}, language = {en} } @article{Kaiser2024, author = {Kaiser, Tobias}, title = {Periods, power series, and integrated algebraic numbers}, series = {Mathematische Annalen}, volume = {390}, journal = {Mathematische Annalen}, number = {2}, publisher = {Springer Berlin Heidelberg}, address = {Berlin/Heidelberg}, issn = {0025-5831}, doi = {10.1007/s00208-024-02802-2}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024040910285674698609}, pages = {2043 -- 2074}, year = {2024}, abstract = {Periods are defined as integrals of semialgebraic functions defined over the rationals. Periods form a countable ring not much is known about. Examples are given by taking the antiderivative of a power series which is algebraic over the polynomial ring over the rationals and evaluate it at a rational number. We follow this path and close these algebraic power series under taking iterated antiderivatives and nearby algebraic and geometric operations. We obtain a system of rings of power series whose coefficients form a countable real closed field. Using techniques from o-minimality we are able to show that every period belongs to this field. In the setting of o-minimality we define exponential integrated algebraic numbers and show that exponential periods and the Euler constant is an exponential integrated algebraic number. Hence they are a good candiate for a natural number system extending the period ring and containing important mathematical constants.}, language = {en} } @phdthesis{Liang2023, author = {Liang, Hanning}, title = {Deflectometric Measurement of the Topography of Reflecting Freeform Surfaces in Motion}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-11672}, school = {Universit{\"a}t Passau}, pages = {xiv, 157 Seiten}, year = {2023}, abstract = {Measuring the topography of specular surfaces with strong surface structures in motion was impossible before this research. A new method based on singleshot phase-measuring de ectometry (SSPMD) and combining different solution aspects has been presented.}, language = {en} } @article{BecherGerl2022, author = {Becher, Stefan and Gerl, Armin}, title = {ConTra Preference Language: Privacy Preference Unification via Privacy Interfaces}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {14}, editor = {Sarne, Giuseppe Maria Luigi and Ma, Jianhua and Rosaci, Domenico and Srivastava, Gautam}, publisher = {MDPI}, address = {Basel, Switzerland}, issn = {1424-8220}, doi = {10.3390/s22145428}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-11218}, pages = {18 Seiten}, year = {2022}, abstract = {After the enactment of the GDPR in 2018, many companies were forced to rethink their privacy management in order to comply with the new legal framework. These changes mostly affect the Controller to achieve GDPR-compliant privacy policies and management.However, measures to give users a better understanding of privacy, which is essential to generate legitimate interest in the Controller, are often skipped. We recommend addressing this issue by the usage of privacy preference languages, whereas users define rules regarding their preferences for privacy handling. In the literature, preference languages only work with their corresponding privacy language, which limits their applicability. In this paper, we propose the ConTra preference language, which we envision to support users during privacy policy negotiation while meeting current technical and legal requirements. Therefore, ConTra preferences are defined showing its expressiveness, extensibility, and applicability in resource-limited IoT scenarios. In addition, we introduce a generic approach which provides privacy language compatibility for unified preference matching.}, language = {en} } @phdthesis{Lachat2024, author = {Lachat, Paul}, title = {Detecting Inference Attacks Involving Sensor Data}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14149}, school = {Universit{\"a}t Passau}, pages = {xiii, 141 Seiten}, year = {2024}, abstract = {The collection of personal information by organizations has become increasingly essential for social interactions. Nevertheless, according to the GDPR (General Data Protection Regulation), the organizations have to protect collected data. Access Control (AC) mechanisms are traditionally used to secure information systems against unauthorized access to sensitive data. The increased availability of personal sensor data, thanks to IoT-oriented applications, motivates new services to offer insights about individuals. Consequently, data mining algorithms have been proposed to infer personal insights from collected sensor data. Although they can be used for genuine purposes, attackers can leverage those outcomes, combining them with other type of data, and further breaching individuals' privacy. Thus, bypassing AC mechanisms thanks to such insights is a concrete problem. We propose an inference detection system based on the analysis of queries issued on a sensor database. The knowledge obtained through these queries, and the inference channels corresponding to the use of data mining algorithms on sensor data to infer individual information, are described using Raw sensor data based Inference ChannEl Model (RICE-M). The detection is carried out by RICE-M based inference detection System (RICE-Sy). RICE-Sy considers at the time of the query, the knowledge that a user obtains via a new query and has obtained via his query history, and determines whether this is sufficient to allow that user to operate a channel. Thus, privacy protection systems can take advantage of the inferences detected by RICE-Sy, taking into account individuals' information obtained by the attackers via a database of sensors, to further protect these individuals.}, language = {en} } @phdthesis{Schlenker2022, author = {Schlenker, Florian}, title = {Delaunay Configuration B-Splines}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-11225}, school = {Universit{\"a}t Passau}, pages = {xxiii, 223 Seiten}, year = {2022}, abstract = {The generalization of univariate splines to higher dimensions is not straightforward. There are different approaches, each with its own advantages and drawbacks. A promising approach using Delaunay configurations and simplex splines is due to Neamtu. After recalling fundamentals of univariate splines, simplex splines, and the wellknown, multivariate DMS-splines, we address Neamtu's DCB-splines. He defined two variants that we refer to as the nonpooled and the pooled approach, respectively. Regarding these spline spaces, we contribute the following results. We prove that, under suitable assumptions on the knot set, both variants exhibit the local finiteness property, i.e., these spline spaces are locally finite-dimensional and at each point only a finite number of basis candidate functions have a nonzero value. Additionally, we establish a criterion guaranteeing these properties within a compact region under mitigated assumptions. Moreover, we show that the knot insertion process known from univariate splines does not work for DCB-splines and reason why this behavior is inherent to these spline spaces. Furthermore, we provide a necessary criterion for the knot insertion property to hold true for a specific inserted knot. This criterion is also sufficient for bivariate, nonpooled DCB-splines of degrees zero and one. Numerical experiments suggest that the sufficiency also holds true for arbitrary spline degrees. Univariate functions can be approximated in terms of splines using the Schoenberg operator, where the approximation error decreases quadratically as the maximum distance between consecutive knots is reduced. We show that the Schoenberg operator can be defined analogously for both variants of DCB-splines with a similar error bound. Additionally, we provide a counterexample showing that the basis candidate functions of nonpooled DCB-splines are not necessarily linearly independent, contrary to earlier statements in the literature. In particular, this implies that the corresponding functions are not a basis for the space of nonpooled DCB-splines.}, subject = {Spline}, language = {en} } @phdthesis{Stier2024, author = {Stier, Julian}, title = {Structure of Artificial Neural Networks : Empirical Investigations}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14968}, school = {Universit{\"a}t Passau}, pages = {xxvi, 350 Seiten}, year = {2024}, abstract = {Within one decade, Deep Learning overtook the dominating solution methods of countless problems of artificial intelligence. "Deep" refers to the deep architectures with operations in manifolds of which there are no immediate observations. For these deep architectures some kind of structure is pre-defined -- but what is this structure? With a formal definition for structures of neural networks, neural architecture search problems and solution methods can be formulated under a common framework. Both practical and theoretical questions arise from closing the gap between applied neural architecture search and learning theory. Does structure make a difference or can it be chosen arbitrarily? This work is concerned with deep structures of artificial neural networks and examines automatic construction methods under empirical principles to shed light on to the so called ``black-box models''. Our contributions include a formulation of graph-induced neural networks that is used to pose optimisation problems for neural architecture. We analyse structural properties for different neural network objectives such as correctness, robustness or energy consumption and discuss how structure affects them. Selected automation methods for neural architecture optimisation problems are discussed and empirically analysed. With the insights gained from formalising graph-induced neural networks, analysing structural properties and comparing the applicability of neural architecture search methods qualitatively and quantitatively we advance these methods in two ways. First, new predictive models are presented for replacing computationally expensive evaluation schemes, and second, new generative models for informed sampling during neural architecture search are analysed and discussed.}, language = {en} } @phdthesis{Juhos2024, author = {Juhos, Michael}, title = {Probabilistic and geometric aspects of classical and non-commutative lp-type spaces in high dimensions}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14857}, school = {Universit{\"a}t Passau}, pages = {viii, 157 Seiten}, year = {2024}, abstract = {This cumulative dissertation contains selected contributions to the field of asymptotic geometric analysis and high-dimensional probability. It is divided into two chapters: Chapter 1 explains some of the necessary theoretical background. In Section 1.1 it first gives a very concise history of asymptotic geometric analysis in general and then of the objects under study in particular, setting out some cornerstones in the discovery of the functional-analytic, geometric, and probabilistic properties of the spaces under consideration. The next section (1.2) gives the precise definitions and very basic properties of the three lp-type spaces that play a role in the contributed articles: the classical lp-sequence spaces, the mixed-norm sequence spaces, and the Schatten-classes Sp, each in its infinite- and finite-dimensional version. Section 1.3 is dedicated to the interplay between geometry and probability, expounding the general idea, introducing a few of the common tools, and exemplifying these on two kinds of limit theorems: Schechtman-Schmuckenschl{\"a}ger-type results and Poincar{\´e}-Maxwell-Borel lemmas. The first chapter concludes with Section 1.4, addressing a small sample of open questions pertaining to the contributed articles which are not answered in said articles and may be the interest of future research. The entirety of Chapter 2 consists of the contributed articles.}, language = {en} } @phdthesis{Auer2024, author = {Auer, Michael}, title = {Improving Automated Android Test Generation}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14955}, school = {Universit{\"a}t Passau}, pages = {x, 140 Seiten}, year = {2024}, abstract = {Mobile apps are nowadays the preferred means to accomplish ubiquitous tasks like messaging, e-commerce and even playing games. Often, there exist multiple apps for the same purpose, and it is the choice of the end user to pick an appropriate app. Apps that behave unexpected, e.g., crash frequently, are sooner or later replaced, which isundesirable for the companies developing such apps. Thus, it is essential to tests apps properly before they are released onto the market. However, testing manually is often not only too cost-intensive but also too time-consuming in the short development phase, thus an automated solution is preferred. Testing mobile apps automatically received increased attention in the last decade from primarily people in academia, and several testing techniques evolved. One technique that yielded promising results, especially in different domains, is search-based software testing in which a metaheuristic, e.g., a genetic algorithm, is applied to solve an optimisation problem, e.g., test generation. A main objective of test generation is to produce tests that reveal as many faults as possible. This in turn requires the generation of tests that deeply explore the tested app. The core metric to quantify how much code tests cover is the measurement of code coverage, which can be computed at different levels of granularity ranging from determining the fraction of covered activities to a very fine-grained measurement that calculates the percentage of covered lines. This coverage information is then often used to guide the search of the employed metaheuristic. However, current automated test generation approaches produce tests with a rather low code coverage. Thus, a substantial part of tested apps remains unexplored, which in turn misses revealing deeply residing faults. We identified three core issues that are directly related to the generation of low-coverage tests. First, the applicability of current test generators is often limited. This comprises the fact that current state-of-the-art code coverage tools are incapable of instrumenting a substantial number of apps and consequently, test generators cannot utilise detailed coverage information during exploration. In addition, test generators are often only equipped with a primitive set of actions that are insufficient to simulate system events and complex user inputs. Second, the test execution is extremely time-consuming. This includes among other things the overhead associated with executing individual actions, intermediate restart operations as well as fitness evaluations. Since search-based algorithms require a substantial number of test executions to play out their strengths, the slow test execution impedes the effectiveness of the search. Third, the guidance offered by search-based algorithms is often hampered by applying inadequate fitness functions or by using non-representation-specific variation operators. In this thesis we address the problem of low-coverage tests in the Android domain by proposing several enhancements for the three identified core issues. Concerning the applicability problem, we provide the implementation of a robust code coverage tool that is capable of measuring coverage at different levels of granularity and requires no access to the source code. We also propose to include actions that can simulate system events as well as complex user inputs. Regarding the performance issue, we suggest the integration of a surrogate model that is capable of predicting the outcome of individual actions or complete tests over time in order to reduce the overall test execution costs. With respect to the lack of guidance offered by traditional search-based algorithms, we suggest alternative search strategies. In the case of a deceptive fitness landscape, we propose using novelty search algorithms. Alternatively, we suggest utilising estimation of distribution algorithms that require no crossover or mutation perators to sample new tests. While all those enhancements had a positive impact on the Android test generation process, the individual empirical studies highlighted that further research is necessary to unleash the full power of the proposed search-based algorithms. In particular, exploring complex user interfaces meaningfully requires more attention whether by introducing additional actions or by extracting valuable hints to infer reasonable text inputs. In addition, the guidance offered by fitness functions is often limited because they are either designed too coarse at all or do not accurately reflect the search objectives.}, language = {en} } @article{LenglerOprisSudholt2024, author = {Lengler, Johannes and Opris, Andre and Sudholt, Dirk}, title = {Analysing Equilibrium States for Population Diversity}, series = {Algorithmica (ISSN: 1432-0541)}, volume = {86}, journal = {Algorithmica (ISSN: 1432-0541)}, number = {7}, publisher = {Springer US}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-024-01226-3}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2406282100292.409184699704}, pages = {2317 -- 2351}, year = {2024}, abstract = {Population diversity is crucial in evolutionary algorithms as it helps with global exploration and facilitates the use of crossover. Despite many runtime analyses showing advantages of population diversity, we have no clear picture of how diversity evolves over time. We study how the population diversity of (μ+1)algorithms, measured by the sum of pairwise Hamming distances, evolves in a fitness-neutral environment. We give an exact formula for the drift of population diversity and show that it is driven towards an equilibrium state. Moreover, we bound the expected time for getting close to the equilibrium state. We find that these dynamics, including the location of the equilibrium, are unaffected by surprisingly many algorithmic choices. All unbiased mutation operators with the same expected number of bit flips have the same effect on the expected diversity. Many crossover operators have no effect at all, including all binary unbiased, respectful operators. We review crossover operators from the literature and identify crossovers that are neutral towards the evolution of diversity and crossovers that are not.}, language = {en} } @article{SchulteLedelHerbold2024, author = {Schulte, Lukas and Ledel, Benjamin and Herbold, Steffen}, title = {Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP}, series = {Empirical Software Engineering (ISSN: 1573-7616)}, volume = {29}, journal = {Empirical Software Engineering (ISSN: 1573-7616)}, number = {4}, publisher = {Springer US}, address = {New York}, issn = {1382-3256}, doi = {10.1007/s10664-024-10469-1}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2409232103207.812648424894}, pages = {29 Seiten}, year = {2024}, abstract = {Context The identification of bugs within issues reported to an issue tracking system is crucial for triage. Machine learning models have shown promising results for this task. However, we have only limited knowledge of how such models identify bugs. Explainable AI methods like LIME and SHAP can be used to increase this knowledge. Objective We want to understand if explainable AI provides explanations that are reasonable to us as humans and align with our assumptions about the model's decision-making. We also want to know if the quality of predictions is correlated with the quality of explanations. Methods We conduct a study where we rate LIME and SHAP explanations based on their quality of explaining the outcome of an issue type prediction model. For this, we rate the quality of the explanations, i.e., if they align with our expectations and help us understand the underlying machine learning model. Results We found that both LIME and SHAP give reasonable explanations and that correct predictions are well explained. Further, we found that SHAP outperforms LIME due to a lower ambiguity and a higher contextuality that can be attributed to the ability of the deep SHAP variant to capture sentence fragments. Conclusion We conclude that the model finds explainable signals for both bugs and non-bugs. Also, we recommend that research dealing with the quality of explanations for classification tasks reports and investigates rater agreement, since the rating of explanations is highly subjective.}, language = {en} } @article{AistleitnerFruehwirthProchno2024, author = {Aistleitner, Christoph and Fr{\"u}hwirth, Lorenz and Prochno, Joscha}, title = {Diophantine conditions in the law of the iterated logarithm for lacunary systems}, series = {Probability Theory and Related Fields (ISSN: 1432-2064)}, volume = {192}, journal = {Probability Theory and Related Fields (ISSN: 1432-2064)}, number = {1}, publisher = {Springer}, address = {Berlin/Heidelberg}, issn = {0178-8051}, doi = {10.1007/s00440-024-01272-6}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2406190937284.886045166092}, pages = {545 -- 574}, year = {2024}, abstract = {It is a classical observation that lacunary function systems exhibit many properties which are typical for systems of independent random variables. However, it had already been observed by Erdős and Fortet in the 1950s that probability theory's limit theorems may fail for lacunary sums (sum f(n_k x)) if the sequence ((n_k)_{k ge 1}) has a strong arithmetic "structure". The presence of such structure can be assessed in terms of the number of solutions k, l of two-term linear Diophantine equations (an_k - bn_l = c). As the first author proved with Berkes in 2010, saving an (arbitrarily small) unbounded factor for the number of solutions of such equations compared to the trivial upper bound, rules out pathological situations as in the Erdős-Fortet example, and guarantees that (sum f(n_k x)) satisfies the central limit theorem (CLT) in a form which is in accordance with true independence. In contrast, as shown by the first author, for the law of the iterated logarithm (LIL) the Diophantine condition which suffices to ensure "truly independent" behavior requires saving this factor of logarithmic order. In the present paper we show that, rather surprisingly, saving such a logarithmic factor is actually the optimal condition in the LIL case. This result reveals the remarkable fact that the arithmetic condition required of ((n_k)_{k ge 1}) to ensure that (sum f(n_k x)) shows "truly random" behavior is a different one at the level of the CLT than it is at the level of the LIL: the LIL requires a stronger arithmetic condition than the CLT does.}, language = {en} } @article{BeurskensScherzinger2024, author = {Beurskens, Michael and Scherzinger, Stefanie}, title = {Legal Perspectives on Research Data Storage}, series = {Datenbank-Spektrum (ISSN: 1618-2162)}, volume = {24}, journal = {Datenbank-Spektrum (ISSN: 1618-2162)}, number = {2}, publisher = {Springer}, address = {Berlin/Heidelberg}, issn = {1618-2162}, doi = {10.1007/s13222-024-00478-1}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2410012125227.647518861484}, pages = {85 -- 95}, year = {2024}, abstract = {Responsibly managing research data has become increasingly important for researchers, especially within the database research community. Despite significant progress in best practices, the state-of-the-art in research data storage is lacking from a legal perspective. We introduce the stakeholders and the dynamic nature of their relationships (such as researchers changing affiliation) and observe that no existing infrastructure for research data storage fully meets their requirements. Therefore, we emphasize the need to design a comprehensive system architecture for research data storage that is aligned with legal considerations from the start, rather than as an afterthought.}, language = {en} } @article{FrankeHeinrichReisch2024, author = {Franke, Jan and Heinrich, Florian and Reisch, Raven T.}, title = {Vision based process monitoring in wire arc additive manufacturing (WAAM)}, series = {Journal of Intelligent Manufacturing (ISSN: 1572-8145)}, volume = {36}, journal = {Journal of Intelligent Manufacturing (ISSN: 1572-8145)}, number = {3}, publisher = {Springer US}, address = {New York}, issn = {0956-5515}, doi = {10.1007/s10845-023-02287-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2405052141549.085870766506}, pages = {1711 -- 1721}, year = {2024}, abstract = {A stable welding process is crucial to obtain high quality parts in wire arc additive manufacturing. The complexity of the process makes it inherently unstable, which can cause various defects, resulting in poor geometric accuracy and material properties. This demands for in-process monitoring and control mechanisms to industrialize the technology. In this work, process monitoring algorithms based on welding camera image analysis are presented. A neural network for semantic segmentation of the welding wire is used to monitor the working distance as well as the horizontal position of the wire during welding and classic image processing techniques are applied to capture spatter formation. Using these algorithms, the process stability is evaluated in real time and the analysis results enable the direction independent closed-loop-control of the manufacturing process. This significantly improves geometric fidelity as well as mechanical properties of the fabricated part and allows the automated production of parts with complex deposition paths including weld bead crossings, curvatures and overhang structures.}, language = {en} } @article{AndraschkoDannerKreuzer2024, author = {Andraschko, Bernhard and Danner, Julian and Kreuzer, Martin}, title = {SAT Solving Using XOR-OR-AND Normal Forms}, series = {Mathematics in Computer Science (ISSN: 1661-8289)}, volume = {18}, journal = {Mathematics in Computer Science (ISSN: 1661-8289)}, number = {4}, publisher = {Springer International Publishing}, address = {Cham}, issn = {1661-8270}, doi = {10.1007/s11786-024-00594-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2502242130589.859216082138}, pages = {26 Seiten}, year = {2024}, abstract = {This paper introduces the XOR-OR-AND normal form (XNF) for logical formulas. It is a generalization of the well-known Conjunctive Normal Form (CNF) where literals are replaced by XORs of literals. As a first theoretic result, we show that every CNF formula is equisatisfiable to a formula in 2-XNF, i.e., a formula in XNF where each clause involves at most two XORs of literals. Subsequently, we present an algorithm which converts Boolean polynomials efficiently from their Algebraic Normal Form (ANF) to formulas in 2-XNF. Experiments with the cipher ASCON-128 show that cryptographic problems, which by design are based strongly on XOR-operations, can be represented using far fewer variables and clauses in 2-XNF than in CNF. In order to take advantage of this compact representation, new SAT solvers based on input formulas in 2-XNF need to be designed. By taking inspiration from graph-based 2-CNF SAT solving, we devise a new DPLL-based SAT solver for formulas in 2-XNF. Among others, we present advanced pre- and in-processing techniques. Finally, we give timings for random 2-XNF instances and instances related to key recovery attacks on round reduced ASCON-128, where our solver outperforms state-of-the-art alternative solving approaches.}, subject = {-}, language = {en} } @article{KoschBrunieMayeretal.2024, author = {Kosch, Harald and Brunie, Lionel and Mayer, Tobias and Hasan, Omar and Schiedermeier, Maximilian}, title = {Anonymous voting using distributed ledger-assisted secure multi-party computation}, series = {Applied Network Science}, volume = {2024}, journal = {Applied Network Science}, number = {9}, publisher = {Springer International Publishing}, address = {Cham (Schweiz)}, doi = {10.1007/s41109-024-00650-2}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15176}, pages = {25 Seiten}, year = {2024}, abstract = {High voter turnout in elections and referendums is desirable to ensure a robust democracy. Secure electronic voting is a vision for the future of elections and referendums. Such a system can counteract factors hindering strong voter turnout such as the requirement of physical presence during limited hours at polling stations. However, this vision brings transparency and confidentiality requirements that render the design of such solutions challenging. Specifically, the counting implementation must support reproducibility, and the choice of individual voters must remain confidential. In this paper, we propose and evaluate a novel referendum protocol that ensures transparency, confidentiality, and integrity, in trustless networks. The protocol is built by combining secure multi-party computation and distributed ledger technology, e.g., a Blockchain. The persistence and immutability of the protocol communication allow verifiability of the referendum outcome by any participant. Voters therefore do not need to trust third parties. We provide a formal description and conduct a thorough security evaluation of our proposal.}, language = {en} } @article{GhodselahiKuhn2023, author = {Ghodselahi, Abdolhamid and Kuhn, Fabian}, title = {Toward Online Mobile Facility Location on General Metrics}, series = {Theory of Computing Systems}, volume = {67}, journal = {Theory of Computing Systems}, number = {6}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00224-023-10145-9}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024022609363705445898}, pages = {1268 -- 1306}, year = {2023}, abstract = {We introduce an online variant of mobile facility location (MFL) (introduced by Demaine et al. (SODA 258-267 2007)). We call this new problem online mobile facility location (OMFL). In the OMFL problem, initially, we are given a set of k mobile facilities with their starting locations. One by one, requests are added. After each request arrives, one can make some changes to the facility locations before the subsequent request arrives. Each request is always assigned to the nearest facility. The cost of this assignment is the distance from the request to the facility. The objective is to minimize the total cost, which consists of the relocation cost of facilities and the distance cost of requests to their nearest facilities. We provide a lower bound for the OMFL problem that even holds on uniform metrics. A natural approach to solve the OMFL problem for general metric spaces is to utilize hierarchically well-separated trees (HSTs) and directly solve the OMFL problem on HSTs. In this paper, we provide the first step in this direction by solving a generalized variant of the OMFL problem on uniform metrics that we call G-OMFL. We devise a simple deterministic online algorithm and provide a tight analysis for the algorithm. The second step remains an open question. Inspired by the k-server problem, we introduce a new variant of the OMFL problem that focuses solely on minimizing movement cost. We refer to this variant as M-OMFL. Additionally, we provide a lower bound for M-OMFL that is applicable even on uniform metrics.}, language = {en} } @article{vonderHeydeGerl2022, author = {von der Heyde, Markus and Gerl, Armin}, title = {Entwicklungsstand der CIO-Funktion und hochschul{\"u}bergreifenden IT-Governance im Kontext der Digitalen Transformation an Hochschulen in Bayern}, series = {HMD Praxis der Wirtschaftsinformatik}, volume = {2022}, journal = {HMD Praxis der Wirtschaftsinformatik}, number = {59}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1365/s40702-022-00872-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2022072222053919381076}, pages = {881 -- 895}, year = {2022}, abstract = {Die Hochschulen befinden sich durch vielf{\"a}ltige Ver{\"a}nderungs-prozesse in Verbindung mit dem Einsatz von Informationstechnologien (IT) aufdem Weg der Digitalen Transformation. Diese Digitale Transformation der Hoch-schulen umfasst intensive Ver{\"a}nderungsprozesse in der gesamten Hochschulkulturin Lehre, Forschung und Verwaltung in {\"u}bergreifender und strukturierter Weise.Seit vielen Jahren werden vielf{\"a}ltige Digitalisierungsvorhaben zur Modernisierungvon einzelnen Prozessen an den Hochschulen umgesetzt. Die Leitungen der Re-chenzentren leisten mit der Umsetzung von IT-Projekten einen zentralen Beitrag zudiesem Wandel. Mit der Einf{\"u}hrung der CIO-Funktion in den Hochschulleitungenund der hochschul{\"u}bergreifenden Kooperationen hat sich die IT-Governance wei-terentwickelt. Insbesondere f{\"u}r die Digitale Transformation werden Strukturen zurKoordination der {\"u}bergreifenden Vorhaben ben{\"o}tigt, wobei zus{\"a}tzlich zur IT-Lei-tung eine Vielzahl von Funktionstr{\"a}gern mit fachlichen Aufgaben aus Forschung,Lehre und Verwaltung involviert ist. Es stellt sich die Frage, wie die Digitale Trans-formation an Hochschulen gesteuert werden kann und in welcher organisatorischenForm sich die Aufgaben und Verantwortlichkeiten im Hochschulkontext realisierenlassen. An der Weiterentwicklung der IT-Governance an bayerischen Hochschulenwird beispielhaft erl{\"a}utert, welche {\"u}bergreifenden Aufgaben der Koordination vonBedarf und Versorgung mit IT-Services zwischen und innerhalb der Hochschulenbestehen. Die CIO-Funktion wird durch die Verankerung in der Leitungsebene derFunktion des Chief Digital Officers (CDO) aus der Wirtschaft {\"a}hnlicher, auch wennin Hochschulen aufgrund der klassischen Ressort-Einteilung die Rolle oft als Vize-pr{\"a}sident:in f{\"u}r Digitalisierung bezeichnet wird.}, language = {de} } @article{HeviaFajardoSudholt2023, author = {Hevia Fajardo, Mario Alejandro and Sudholt, Dirk}, title = {Self-adjusting Population Sizes for Non-elitist Evolutionary Algorithms: why Success Rates Matter}, series = {Algorithmica}, volume = {86}, journal = {Algorithmica}, number = {2}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00453-023-01153-9}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023102616463077837436}, pages = {526 -- 565}, year = {2023}, abstract = {Evolutionary algorithms (EAs) are general-purpose optimisers that come with several parameters like the sizes of parent and offspring populations or the mutation rate. It is well known that the performance of EAs may depend drastically on these parameters. Recent theoretical studies have shown that self-adjusting parameter control mechanisms that tune parameters during the algorithm run can provably outperform the best static parameters in EAs on discrete problems. However, the majority of these studies concerned elitist EAs and we do not have a clear answer on whether the same mechanisms can be applied for non-elitist EAs. We study one of the best-known parameter control mechanisms, the one-fifth success rule, to control the offspring population size λ in the non-elitist (1, λ) EA. It is known that the (1, λ) EA has a sharp threshold with respect to the choice of λ where the expected runtime on the benchmark function OneMax changes from polynomial to exponential time. Hence, it is not clear whether parameter control mechanisms are able to find and maintain suitable values of λ. For OneMax we show that the answer crucially depends on the success rates (i. e. a one-(s + 1)-th success rule). We prove that, if the success rate is appropriately small, the self-adjusting (1, λ) EA optimises OneMax in O(n) expected generations and O(n log n) expected evaluations, the best possible runtime for any unary unbiased black-box algorithm. A small success rate is crucial: we also show that if the success rate is too large, the algorithm has an exponential runtime on OneMax and other functions with similar characteristics.}, language = {en} } @article{GaginBettermanndeMeer2023, author = {Gagin, Stepan and Bettermann, Michael and de Meer, Hermann}, title = {Multi-vector optimization scheme for distributed components in energy islands}, series = {e+i Elektrotechnik und Informationstechnik}, volume = {140}, journal = {e+i Elektrotechnik und Informationstechnik}, number = {5}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00502-023-01145-1}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023110413071966670578}, pages = {460 -- 470}, year = {2023}, abstract = {Recent advancements in energy systems, such as the emergence of prosumers and sector coupling approaches, introduce additional flexibilities over multiple energy sectors, such as heating, electricity, and mobility. Due to the complexity of such distributed systems, the optimization of energy allocation is a non-trivial task, especially considering constraints and limitations introduced by distributed devices or sub-systems. Additionally, the variety of devices forces approaches to be highly situational and not universally applicable. In this paper, a two-level optimization scheme is proposed, which aims at reducing the optimization complexity of sector-coupled systems. The multi-vector optimization embedded in the two-level optimization scheme is formulated as a mixed-integer linear problem, optimizing the energy flow between domains, which are modeled as an abstraction of a sector. Distributed devices are modeled as components that represent an abstraction of devices connected to an energy domain. The optimization process is evaluated based on the data from a residential complex in Ghent, Belgium. It shows that the approach is capable of minimizing costs, CO2 emissions, and dependency on external resources.}, language = {en} } @article{FinkForsterHeinrich2023, author = {Fink, Thomas and Forster, Brigitte and Heinrich, Florian}, title = {Gabor's "complex signal" revisited: Complexifying frames and bases}, series = {PAMM (Proceedings in Applied Mathematics and Mechanics)}, volume = {23}, journal = {PAMM (Proceedings in Applied Mathematics and Mechanics)}, number = {3}, publisher = {Wiley}, address = {Hoboken}, doi = {10.1002/pamm.202300155}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023091815015485698899}, pages = {8}, year = {2023}, abstract = {In 1946, Dennis Gabor introduced the analytic signal 𝑓 + 𝑖𝐻𝑓 for real-valued signals 𝑓. Here, 𝐻 is the Hilbert transform. This complexification of functions allows for an analysis of their amplitude and phase information and has ever since given well-interpretable insight into the properties of the signals over time. The idea of complexification has been reconsidered with regard to many aspects: examples are the dual tree complex wavelet transform, or via the Riesz transform and the monogenic signal, that is, a multi-dimensional version of the Hilbert transform, which in combination with multi-resolution approaches leads to Riesz wavelets, and others. In this context, we ask two questions: - Which pairs of real orthonormal bases (ONBs), Riesz bases, frames and Parseval frames {𝑓 𝑛 } 𝑛∈ℕ and {𝑔 𝑛 } 𝑛∈ℕ can be "rebricked" to complex-valued ones {𝑓𝑛 + 𝑖𝑔 𝑛 } 𝑛∈ℕ? - And which real operators A allow for rebricking via the ansatz {𝑓𝑛 + 𝑖𝐴𝑓𝑛 } 𝑛∈ℕ? In this short note, we give answers to these questions with regard to a characterization which linear operators A are suitable for rebricking while maintaining the structure of the original real valued family. Surprisingly, the Hilbert transform is not among them.}, language = {en} } @phdthesis{Stumpf2024, author = {Stumpf, Peter Frederik}, title = {Partial Representation Extension and Simultaneous Representation of Intersection Graphs}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15201}, school = {Universit{\"a}t Passau}, pages = {IX, 208 Seiten}, year = {2024}, abstract = {Many real world problems can be modeled with geometric intersection graphs. A (geometric) intersection representation of a graph G=(V,E) is a family {R_v}_{v\in V} of geometric objects such that two geometric objects R_u, R_v intersect if and only if the corresponding vertices u, v are adjacent in G. The most prominent class of intersection graphs are interval graphs, which have representations consisting only of intervals on the real line. Interval graphs have applications in genetics, scheduling, archaeology and many more fields. The recognition problem asks the question whether a given graph belongs to a certain graph class. Two natural generalizations of the recognition problem are the partial representation extension problem and the simultaneous representation problem. In the partial representation extension problem one is given a graph G and a partial representation, i.e., a representation of a subgraph of G. The question then is whether the partial representation can be extended to the whole graph G without changing the given partial representation. In the simultaneous representation problem one is given multiple graphs G_1,...,G_k that can have shared parts, and the question is whether there are representations of all input graphs such that shared vertices are represented by the same geometric objects. Often the sunflower case is considered, where the shared part of any two input graphs is the same. We determine the complexity of the partial representation extension problem and the simultaneous representation problem, especially in the sunflower case for various intersection graph classes. We also improve the running time for various intersection graph classes. In particular, we show that the partial representation extension problem for circular-arc graphs is NP-complete and that the simultaneous representation problem for interval graphs can be solved in linear time in the sunflower case, answering open questions from 2014 and 2010.}, language = {en} } @phdthesis{GhoshDastidar2025, author = {Ghosh Dastidar, Kanishka}, title = {Using Context for Credit Card Fraud Detection}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15561}, school = {Universit{\"a}t Passau}, pages = {147 Seiten}, year = {2025}, abstract = {Online payment fraud is one of the biggest challenges accompanying the ubiquitous adoption of digital payment methods. The academic literature shows that providing data-driven models with additional context of a transaction results in significant improvements in fraud detection performance. However, the methods used to generate suitable context representations often rely on human expert knowledge, which is expensive and suffers from several limitations. In this thesis, we propose different methods to automate this process by learning these context representations end-to-end on the fraud detection objective. Each of these methods is evaluated on millions of real-world transactions from Worldline, our industrial partner. Central to this thesis is our proposal of the Neural Aggregate Generator (NAG), a neural network that learns context representations automatically. The architecture of the NAG is designed to resemble the structure of expert feature aggregates, while also addressing their limitations. Our evaluation of the NAG reveals that it outperforms both approaches that use expert aggregates and other end-to-end methods across several months of testing. A thorough evaluation shows that the NAG improves over other approaches on several key factors including model size and robustness to shorter sequences. We propose several extensions to the NAG with the dual motive of improved alignment with expert aggregates and improved expressiveness. Our evaluation of these extensions shows comparable performance to the NAG with ancillary benefits in terms of prospective interpretability and model size. We also introduce the novel paradigm of using \lq future' transactions as context. Our analysis of real-world data from Worldline shows that verification of transactions are often delayed by several days and that within this delay there are often several transactions booked on the card which can be used as additional context. We show that this future context improves the performance of sequence models. Moreover, we also show that a balance between past and future context yields the best results and that using future context allows the use of shorter sequences overall. Beyond context-based fraud detection, we also provide an initial proposal of generating synthetic credit card data using Generative Adversarial Networks (GANs), showing that a Wasserstein GAN can be used to generated synthetic data similar to a popular publicly available credit card fraud dataset. We also describe several possible directions for future work including the incorporation of a adapted self-attention mechanism to the NAG and the use of transformers for synthetic data generation.}, language = {en} } @phdthesis{Soller2025, author = {Soller, Sebastian}, title = {Anomaly Detection and Forecasting Techniques and their Applications Scenarios, Challenges and Limits in Industrial Production Settings}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15659}, school = {Universit{\"a}t Passau}, pages = {vi, 136 Seiten}, year = {2025}, abstract = {What needs to be done to get machine learning and artificial intelligence from the lab to the shop floor? This work and its affiliated publications focus on challenges and solutions to apply machine learning applications inside industrial setups and what steps are needed to improve those setups. In industrial setups it is easy to run into a "hen and egg" problem. To gather data, the information which data to gather is ideally given beforehand and these information are not available when studying new setups and machines. In this work setups and concepts are created to dynamically connect to a network and start gathering data from available endpoints inside a manufacturing setup. The data streams of these endpoints are further analyzed to give an initial analysis of the data and advise further processing. To further analyze these data streams with the current advances in the machine learning field and AI, plug and play solutions are presented by manufacturers and scientific research. Limits are determined for this plug and play capability and solutions are provided to further improve upon the base solutions. The capability to apply commonly applied methods was analyzed and initially provided non-sufficient results. In the sub-fields of anomaly detection, regression analysis, forecasting and classification the addition of context information, such as production specific information and time dependent analysis were used to improve the results. Context information, especially periodic information, were further conceptualized and integrated into the initial data analysis. Difficulties with correct labeling of ground truth due to differing biases of participants were encountered, and counter measurements were proposed. Results of the classification, regression, forecast and context information extraction were investigated for their influence on the human operator. A significant change could be measured in multiple cases, just by providing information about underlying problems and errors. The Aforementioned machine learning methods further improved the performance of machine and operator.}, subject = {Anomalieerkennung}, language = {en} } @phdthesis{Fruehwirth2025, author = {Fr{\"u}hwirth, Lorenz}, title = {The Asymptotic Behavior of Birkhoff- and Lacunary Sums}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15677}, school = {Universit{\"a}t Passau}, pages = {109 Seiten}, year = {2025}, abstract = {This doctoral thesis consists of three independently published research articles on the asymptoic behaviour of Lacunary- and Birkhoff sums. The former are sums formed by periodic functions and exponentially growing sequences of natural numbers. The corresponding summands often exhibit behavior typical of independent and identically distributed random variables. The methods used are of an analytical and probabilistic nature. The Birkhoff sums considered in this work are generated by the Kronecker sequence and by discontinuous functions. The methods employed are from the field of metric number theory, specifically classical results from continued fraction theory are utilized.}, language = {en} } @misc{MexisLillDolehetal.2025, author = {Mexis, Nico and Lill, Bjarne and Doleh, Yousef and Katzenbeisser, Stefan}, title = {Supplementary Material for the Work "Exposing the Gaps: The State of Supply Chain Coverage in Current Security Standards"}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15633}, pages = {29 Seiten}, year = {2025}, abstract = {This document contains the supplementary material for our work "Exposing the Gaps: The State of Supply Chain Coverage in Current Security Standards", which should be consulted for further information and details. While this supplement has not been peer-reviewed, the above article has. The reviewers also had access to all the data presented in this document during the review phase. The article is available from 26 July 2025 as part of the "IFIP Advances in Information and Communication Technology", volume 742: 10.1007/978-3-031-94924-1_14}, subject = {Supply Chain Management}, language = {en} } @phdthesis{Raich2025, author = {Raich, Krispin}, title = {Multimodal Data Space for Cooperative Intelligent Transport Systems}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15496}, school = {Universit{\"a}t Passau}, pages = {xv, 111 Seiten}, year = {2025}, abstract = {Modern Cooperative Intelligent Transport Systems (C-ITSs) are comprehensive applications that must cope with a multitude of challenges while meeting strict service and security standards. One of these challenges is a fast, secure, reliable, and universal way to store and exchange data in such a traffic system. Furthermore, multimodal scenarios where different types of vehicles (e.g., cars and Unmanned Aerial System) interact with each other, are increasingly emerging. To overcome these challenges, this thesis presents a set of key innovations to establish a multimodal capable data space for transport application. Therefore, a multimodal optimized geographic model is presented, called SpatialJSON, that is capable of depicting two- and three-dimensional geometries. To accomplish this feat, SpatialJSON extends the popular GeoJSON format with two new data types: area and corridor. Exchanging, managing, and storing data is handled in a novel data-centric middleware, called Large Scale Multimodal Data Processing Middleware for Intelligent Transport Systems (LDPM). This LDPM uses cryptographic- and trust-based schemas to allow secure data exchange and provide data quality assessment. Furthermore, a service architecture is introduced, that fulfils modern service requirements. Trust management is also another essential part of a C-ITS. Hence, a novel scheme to describe traffic related evidence in a multimodal environment is introduced. This schema allows assessing arbitrary traffic related data. This information is then processed in a specialized and modified Bayesian Inference (BI) function. Subsequently, a comprehensive data centric trust management method is introduced. Finally, a use case is presented that relies on the aforementioned technologies to collect data in a hazardous environmental. This data is then distributed and managed via the LDPM, and finally visualized.}, language = {en} } @phdthesis{Julka2025, author = {Julka, Sahib}, title = {Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-16030}, school = {Universit{\"a}t Passau}, pages = {20 ungez{\"a}hlte Seiten, 131 Seiten, 17 ungez{\"a}hlte Seiten}, year = {2025}, abstract = {The deployment of artificial intelligence (AI) in specialised domains such as planetary science and healthcare, as well as in low-resource NLP settings, faces two fundamental challenges: label scarcity and data scarcity. Label scarcity stems from the high cost of expert annotation, the scarcity of domain experts, and the infeasibility of crowdsourcing, particularly in complex tasks requiring specialised knowledge. In parallel, data scarcity stems from the inherent difficulty of acquiring sufficient raw data, whether due to limited observational opportunities, environmental and technical barriers, or stringent privacy constraints. Together, these limitations impede the broader adoption of AI in these fields. Many existing approaches to label efficiency, such as active learning, rely on problem-specific heuristics and often, as a design choice, employ naive uncertainty estimations—typically at the instance level. However, such methods can lead to redundant or suboptimal sample selection by ignoring structural data properties and failing to account for representational diversity. In practice, they often perform no better than random sampling. For data synthesis, generative models face their own set of challenges. Despite their promise for synthetic data generation, these models frequently lack mechanisms to disentangle generative factors at the representation level, limiting their controllability. Additionally, standardised evaluation metrics to assess the quality of disentanglement remain underdeveloped, limiting their practical utility. These limitations highlight the need for advancements in data-efficient machine learning and controllable generative modelling, focusing on domain-specific validity and rigorous evaluation. This thesis contributes to addressing these challenges by proposing tailored solutions in two key directions. First, for data-efficient learning, a deep active learning (DAL) framework is introduced to enhance label efficiency by prioritising the most informative samples for annotation. Unlike traditional per-sample approaches, this framework aggregates uncertainty across larger data segments—such as orbital intervals in planetary science—allowing it to capture contextual variations. This method reduces labelled data requirements by up to 90\% in the case of boundary crossing detection at Mercury's magnetosphere. To further improve sampling diversity, a GAN-based concept drift detection method is integrated into the DAL framework, leveraging uncertainty and diversity together to offer a sampling method that outperforms random sampling. Additionally, foundation models such as the Segment Anything Model (SAM) are employed for zero-shot annotation to generate high-quality pseudo-labels, which are subsequently used to train a domain-specific model via knowledge distillation. This approach significantly enhances data efficiency, reducing the need for annotated samples several times over in the tested scenario of image segmentation for geological mapping. Furthermore, large language models (LLMs) are explored as active annotators for linguistic tasks in low-resource languages, achieving near-baseline performance while reducing annotation costs by up to 40x. Second, the thesis investigates methods to induce controllability in generative models, enabling the production of high-fidelity, controllable synthetic data. Conditional generative adversarial networks (CGANs) and disentangled representation learning techniques (DRL) are explored, particularly in the context of pedestrian trajectory prediction in the mobility domain, where controlled synthesis of diverse motion patterns is critical. Additionally, the work examines existing metrics for evaluating disentanglement and identifies critical limitations in them. A novel metric, the Exclusivity Disentanglement Index (EDI), is proposed as an improved standardised measure. Based on the principle of exclusivity in factor-code relationships, this metric offers advantages over existing alternatives in terms of efficiency and robustness. By advancing data-efficient learning and controllable generation strategies, this thesis aims to bridge the gap between AI's vast potential and its practical adoption in resource-constrained environments. These contributions pave the way for transformative applications in planetary science, healthcare, and beyond, where label and data scarcity have long been barriers to progress.}, language = {en} } @phdthesis{Wilhelm2025, author = {Wilhelm, Sebastian}, title = {Emergency Detection in Private Households Utilizing Existing Data Sources for Human Activity Event Recognition}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15992}, school = {Universit{\"a}t Passau}, pages = {xvii, 156 Seiten}, year = {2025}, abstract = {In an aging society, the need for efficient emergency detection systems in smart homes is becoming increasingly important. Over 30\% of those aged 65 and older experience at least one fall per year, often resulting in the inability to rise without assistance, leading to 'long lies' lasting hours or even days. Systems for detecting such emergency events usually rely on wearable sensors or specific installations of ambient sensors, which can be intrusive and complex, hindering acceptance. This thesis proposes a novel approach that utilizes existing digital data sources within the residential infrastructure to detect human activities and identify potential emergencies. A survey identifies 44 potential data sources in private households for recognizing human activity. However, extracting activity information often requires complex preprocessing. In this thesis, methodologies are developed for three of these data sources to highlight practical applications: Smart Power Meters, Smart Water Meters, and Home Weather Stations. It is shown that detecting human activities using these sources is feasible in a practical environment, although accuracy and reliability vary. Notably, Smart Water Meters demonstrate high reliability, with a precision of 0.86 and a recall of 1.00, making them particularly suitable for emergency detection. Existing emergency detection methods are not designed to handle uncertain activity data. This thesis introduces a novel approach based on probabilistic activity information, employing an Inactivity Score that provides a probabilistic weighting of inactivity periods based on the reliability of sensor measurements. By analyzing historical Inactivity Scores, anomalies that potentially represent an emergency can be identified. Evaluations across seven datasets show this approach outperforms existing methods, achieving a mean time to detect emergencies of approximately 05:23:28 hours and producing 0.09 false positives per day under noise-free conditions. Moreover, unlike related approaches, the proposed method remains effective with noisy data. This thesis demonstrates that emergencies in private households can be detected using existing data sources from the home infrastructure, offering a cost-effective and non-intrusive solution to enhance the safety and autonomy of the elderly at home.}, language = {de} } @phdthesis{Hasenpflug2025, author = {Hasenpflug, Mareike}, title = {Slice sampling on Riemannian manifolds}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15903}, school = {Universit{\"a}t Passau}, pages = {iii, 118 Seiten}, year = {2025}, abstract = {This thesis is concerned with hybrid slice samplers for approximate sampling of distributions on Riemannian manifolds. First for distributions on the Euclidean unit sphere, and then for distributions on general Riemannian manifolds we introduce a geodesic-based hybrid slice sampler, called geodesic slice sampler. Under mild regularity assumptions, we establish reversibility with respect to the target distribution for this sampler and positive semi-definiteness of the corresponding operator. Moreover, on compact Riemannian manifolds we show uniform ergodicity with explicit constants for the geodesic slice sampler if the target distribution has a bounded density with respect to the Riemannian measure. As an important building block of this sampler, we provide an explicit expression for the shrinkage procedure proposed in (Neal, 2003) in terms of a Markov kernel. We establish that this kernel is reversible with respect to the uniform distribution on the target set and that its corresponding operator is positive semi-definite. Beyond the geodesic slice sampler, we apply these results also to elliptical slice sampling (Murray, Adams, MacKay, 2010) to obtain a proof for its reversibility with respect to the target distribution and positive semi-definiteness of the corresponding operator.}, language = {en} } @article{GoshDastidarCaelenGranitzer2024, author = {Gosh Dastidar, Kanishka and Caelen, Olivier and Granitzer, Michael}, title = {Machine learning methods for credit card fraud detection : a survey}, series = {IEEE Access}, volume = {2024}, journal = {IEEE Access}, number = {12}, publisher = {IEEE}, address = {New York}, doi = {10.1109/ACCESS.2024.348729}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15796}, pages = {158939 -- 158965}, year = {2024}, abstract = {The widespread adoption of online payments has been accompanied by a significant increase in fraudulent activities, resulting in billions of dollars in financial losses. As payment providers aim to tackle this with various preventive mechanisms, fraudsters also continuously evolve their methods to remain indistinguishable from genuine actors. This necessitates sophisticated fraud detection tools to supplement these security mechanisms. As the volume of transactions taking place per day is in the millions, relying solely on human investigation is expensive and ultimately unfeasible, leading to an emergence of research into data driven or statistical methods for fraud detection. Over the last decade, this research has evolved to tackle the various particularities of the domain. These include the skewed nature of the data, the evolving user and fraud behavior, and the learning representations of the context in which a transaction takes place. This work aims to provide the community with an in-depth overview of the different directions in which recent research on online fraud detection has focused. We develop a taxonomy of the domain based on these directions and organize our analysis accordingly. For each area, we focus on significant methodological advancements and highlight limitations or gaps in the current state-of-the-art solutions. Through our analysis, it emerges that one of the primary limiting factors that many researchers face is the lack of availability of high-quality credit card data. Therefore, we provide a first step in addressing this issue in the form of a data generation framework using generative adversarial networks (GANs). We hope that this survey serves as a foundation for researchers who want to address the multi-faceted problem of credit card fraud detection.}, language = {en} } @article{LukasczykKroissFraser2023, author = {Lukasczyk, Stephan and Kroiß, Florian and Fraser, Gordon}, title = {An empirical study of automated unit test generation for Python}, series = {Empirical Software Engineering}, volume = {28}, journal = {Empirical Software Engineering}, number = {1}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10664-022-10248-w}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023081721042349746457}, pages = {1 -- 46}, year = {2023}, abstract = {Various mature automated test generation tools exist for statically typed programming languages such as Java. Automatically generating unit tests for dynamically typed programming languages such as Python, however, is substantially more difficult due to the dynamic nature of these languages as well as the lack of type information. Our P YNGUIN framework provides automated unit test generation for Python. In this paper, we extend our previous work on P YNGUIN to support more aspects of the Python language, and by studying a larger variety of well-established state of the art test-generation algorithms, namely DynaMOSA, MIO, and MOSA. Furthermore, we improved our P YNGUIN tool to generate regression assertions, whose quality we also evaluate. Our experiments confirm that evolutionary algorithms can outperform random test generation also in the context of Python, and similar to the Java world, DynaMOSA yields the highest coverage results. However, our results also demonstrate that there are still fundamental remaining issues, such as inferring type information for code without this information, currently limiting the effectiveness of test generation for Python.}, language = {en} } @article{TrautschErbelHerboldetal.2023, author = {Trautsch, Alexander and Erbel, Johannes and Herbold, Steffen and Grabowski, Jens}, title = {What really changes when developers intend to improve their source code: a commit-level study of static metric value and static analysis warning changes}, series = {Empirical Software Engineering}, volume = {28}, journal = {Empirical Software Engineering}, number = {2}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10664-022-10257-9}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023032321174386000821}, pages = {1 -- 40}, year = {2023}, language = {en} } @article{Mironchenko2023, author = {Mironchenko, Andrii}, title = {Well-posedness and properties of the flow for semilinear evolution equations}, series = {Mathematics of Control, Signals, and Systems}, volume = {36}, journal = {Mathematics of Control, Signals, and Systems}, number = {3}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00498-023-00378-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024022307494197431619}, pages = {483 -- 523}, year = {2023}, abstract = {We derive conditions for well-posedness of semilinear evolution equations with unbounded input operators. Based on this, we provide sufficient conditions for such properties of the flow map as Lipschitz continuity, bounded-implies-continuation property, boundedness of reachability sets, etc. These properties represent a basic toolbox for stability and robustness analysis of semilinear boundary control systems. We cover systems governed by general C0 -semigroups, and analytic semigroups that may have both boundary and distributed disturbances. We illustrate our findings on an example of a Burgers' equation with nonlinear local dynamics and both distributed and boundary disturbances.}, language = {en} } @article{HerboldTunkel2023, author = {Herbold, Steffen and Tunkel, Steffen}, title = {Differential testing for machine learning: an analysis for classification algorithms beyond deep learning}, series = {Empirical Software Engineering}, volume = {28}, journal = {Empirical Software Engineering}, number = {2}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s10664-022-10273-9}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023033121421148821912}, pages = {1 -- 38}, year = {2023}, abstract = {Differential testing is a useful approach that uses different implementations of the same algorithms and compares the results for software testing. In recent years, this approach was successfully used for test campaigns of deep learning frameworks. There is little knowledge about the application of differential testing beyond deep learning. Within this article, we want to close this gap for classification algorithms. We conduct a case study using Scikit-learn, Weka, Spark MLlib, and Caret in which we identify the potential of differential testing by considering which algorithms are available in multiple frameworks, the feasibility by identifying pairs of algorithms that should exhibit the same behavior, and the effectiveness by executing tests for the identified pairs and analyzing the deviations. While we found a large potential for popular algorithms, the feasibility seems limited because, often, it is not possible to determine configurations that are the same in other frameworks. The execution of the feasible tests revealed that there is a large number of deviations for the scores and classes. Only a lenient approach based on statistical significance of classes does not lead to a huge amount of test failures. The potential of differential testing beyond deep learning seems limited for research into the quality of machine learning libraries. Practitioners may still use the approach if they have deep knowledge about implementations, especially if a coarse oracle that only considers significant differences of classes is sufficient.}, language = {en} } @article{RudolfSchaer2023, author = {Rudolf, Daniel and Sch{\"a}r, Philip}, title = {Dimension-independent spectral gap of polar slice sampling}, series = {Statistics and Computing}, volume = {34}, journal = {Statistics and Computing}, number = {1}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s11222-023-10335-y}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024011821064231531382}, pages = {14 Seiten}, year = {2023}, abstract = {Polar slice sampling, a Markov chain construction for approximate sampling, performs, under suitable assumptions on the target and initial distribution, provably independent of the state space dimension. We extend the aforementioned result of Roberts and Rosenthal (Stoch Model 18(2):257-280, 2002) by developing a theory which identifies conditions, in terms of a generalized level set function, that imply an explicit lower bound on the spectral gap even in a general slice sampling context. Verifying the identified conditions for polar slice sampling yields a lower bound of 1/2 on the spectral gap for arbitrary dimension if the target density is rotationally invariant, log-concave along rays emanating from the origin and sufficiently smooth. The general theoretical result is potentially applicable beyond the polar slice sampling framework.}, language = {en} } @article{WeissgerberBenAmorFelliciousetal.2023, author = {Weißgerber, Thomas and Ben Amor, Mehdi and Fellicious, Christofer and Granitzer, Michael}, title = {PyPads: Transparent Machine Learning Experiment Tracking}, series = {Datenbank-Spektrum}, volume = {24}, journal = {Datenbank-Spektrum}, number = {1}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s13222-023-00459-w}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2024021511222778687954}, pages = {53 -- 62}, year = {2023}, abstract = {Despite algorithmic advancements in the field of machine learning, a need for improvement in the infrastructure supporting machine learning development and research has become increasingly apparent. Machine learning experiments usually tend to be more ad-hoc in nature, and results are communicated most often in the form of a publication. Experimental details are often omitted due to size or time constraints, or simply because the complexity in terms of technical setup or parametrization became intractable. Even access to code bases, disregard important properties of the environment and experimental setup, like for example random generators or computing infrastructure. At the same time, tracking and communicating an often inherently exploratory scientific process is a task with considerable effort. We explored different venues to tackle these issues from a data science engineering point of view. The efforts resulted in PyPads, a framework providing an infrastructure to extend experimental setups with logging, communication and analysis features in a mostly non-intrusive way. PyPads can be extended to different Python-based frameworks, utilizing community driven, descriptive metadata in an effort to harmonize library specific logs in an ontology. Meanwhile, we also try to emphasize similarities to practices in software engineering, which have turned out to be essential in practical applications.}, language = {en} } @misc{Mexis2023, type = {Master Thesis}, author = {Mexis, Nico}, title = {A Comprehensive Comparison of Fuzzy Extractor Schemes Employing Different Error Correction Codes}, volume = {2023}, doi = {10.15475/ccfesedecc.2023}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-12914}, school = {Universit{\"a}t Passau}, pages = {vii, 100 Seiten}, year = {2023}, abstract = {This thesis deals with fuzzy extractors, security primitives often used in conjunction with Physical Unclonable Functions (PUFs). A fuzzy extractor works in two stages: The generation phase and the reproduction phase. In the generation phase, an Error Correction Code (ECC) is used to compute redundant bits for a given PUF response, which are then stored as helper data, and a key is extracted from the response. Then, in the reproduction phase, another (possibly noisy) PUF response can be used in conjunction with this helper data to extract the original key. It is clear that the performance of the fuzzy extractor is strongly dependent on the underlying ECC. Therefore, a comparison of ECCs in the context of fuzzy extractors is essential in order to make them as suitable as possible for a given situation. It is important to note that due to the plethora of various PUFs with different characteristics, it is very unrealistic to propose a single metric by which the suitability of a given ECC can be measured. First, we give a brief introduction to the topic, followed by a detailed description of the background of the ECCs and fuzzy extractors studied. Then, we summarise related work and describe an implementation of the ECCs under consideration. Finally, we carry out the actual comparison of the ECCs and the thesis concludes with a summary of the results and suggestions for future work.}, subject = {Vorw{\"a}rtsfehlerkorrektur}, language = {en} } @article{ErdoganHassen, author = {Erdogan, G{\"u}lsah and Hassen, Wiem Fekih}, title = {Charging scheduling of hybrid energy storage systems for EV charging stations}, series = {Energies}, volume = {2023}, journal = {Energies}, number = {16}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/en16186656}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-14128}, pages = {29 Seiten}, abstract = {The growing demand for electric vehicles (EV) in the last decade and the most recent European Commission regulation to only allow EV on the road from 2035 involved the necessity to design a cost-effective and sustainable EV charging station (CS). A crucial challenge for charging stations arises from matching fluctuating power supplies and meeting peak load demand. The overall objective of this paper is to optimize the charging scheduling of a hybrid energy storage system (HESS) for EV charging stations while maximizing PV power usage and reducing grid energy costs. This goal is achieved by forecasting the PV power and the load demand using different deep learning (DL) algorithms such as the recurrent neural network (RNN) and long short-term memory (LSTM). Then, the predicted data are adopted to design a scheduling algorithm that determines the optimal charging time slots for the HESS. The findings demonstrate the efficiency of the proposed approach, showcasing a root-mean-square error (RMSE) of 5.78\% for real-time PV power forecasting and 9.70\% for real-time load demand forecasting. Moreover, the proposed scheduling algorithm reduces the total grid energy cost by 12.13\%.}, language = {en} } @article{FruehwirthJuhosProchno2022, author = {Fr{\"u}hwirth, Lorenz and Juhos, Michael and Prochno, Joscha}, title = {The large deviation behavior of lacunary sums}, series = {Monatshefte f{\"u}r Mathematik}, volume = {2022}, journal = {Monatshefte f{\"u}r Mathematik}, number = {199}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.1007/s00605-022-01733-x}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2022081723261050522140}, pages = {113 -- 133}, year = {2022}, abstract = {We study the large deviation behavior of lacunary sums (Sn /n)n∈N with Sn :=∑[k=1...n] f (a(k)U), n ∈ |N, where U is uniformly distributed on [0, 1], (a(k))k∈|N is an Hadamard gap sequence, and f : |R → |R is a 1-periodic, (Lipschitz-)continuous mapping. In the case of large gaps, we show that the normalized partial sums satisfy a large deviation principle at speed n and with a good rate function which is the same as in the case of independent and identically distributed random variables U(k), k ∈ |N, having uniform distribution on [0, 1]. When the lacunary sequence (a(k))k∈|N is a geometric progression, then we also obtain large deviation principles at speed n, but with a good rate function that is different from the independent case, its form depending in a subtle way on the interplay between the function f and the arithmetic properties of the gap sequence. Our work generalizes some results recently obtained by Aistleitner, Gantert, Kabluchko, Prochno, and Ramanan [Large deviation principles for lacunary sums, preprint, 2020] who initiated this line of research for the case of lacunary trigonometric sums.}, language = {en} }