TY - CHAP A1 - Knierim, Pascal A1 - Prange, Sarah A1 - Alt, Florian A1 - Feger, Sebastian A1 - Schneegass, Stefan A1 - Sasse, M. Angela A1 - Bayerl, Dominik A1 - Hof, Hans-Joachim ED - Marky, Karola ED - Grünefeld, Uwe ED - Kosch, Thomas T1 - Inclusive Security by Design T2 - Mensch und Computer 2022 - Workshopband UR - https://doi.org/10.18420/muc2022-mci-ws14-128 KW - usable security KW - inclusion KW - self-determined security Y1 - 2022 UR - https://doi.org/10.18420/muc2022-mci-ws14-128 PB - Gesellschaft für Informatik e.V. CY - Bonn ER - TY - CHAP A1 - Bayerl, Dominik A1 - Hutzelmann, Thomas A1 - Hof, Hans-Joachim T1 - Efficient Cross-Architecture Binary Function Embeddings through Knowledge Distillation T2 - Proceedings of the 11th ACM Cyber-Physical System Security Workshop N2 - Deep learning has recently been shown to be effective in various tasks related to static binary analysis. One important analysis task is the binary function similarity problem: Given the binary code of two functions compiled with different compilers, different settings, and different processor architectures, the goal is to decide whether the functions are semantically equivalent (i.e. "similar") or not. This problem has numerous applications for embedded systems, for example plagiarism detection, validation of compliance restrictions with usable software licenses, more efficient reverse engineering of existing binary codebases, or vulnerability scanning by detecting known vulnerable functions. In this paper, we propose a novel training scheme for the popular transformer neural network architecture to learn function embeddings directly from instruction listings. Unlike existing approaches, our solution explicitly considers the cross-architecture scenario: we propose a training method to adapt the model to different instruction set architectures (ISA) without having to train a new model from scratch, which allows the model to also be used efficiently for embedded systems, where there are a variety of different processor architectures. We show that our solution achieves a similarity classification accuracy of 89.6% on a dataset consisting of several real-world open source software projects. Finally, we conduct extensive experiments to demonstrate the effectiveness of knowledge distillation in increasing the computational efficiency of the embedding model. We demonstrate a reduction in the number of parameters from 87M to 23M, while still maintaining a classification accuracy of 87.8%. Our code and artifacts are available as open source. UR - https://doi.org/10.1145/3709017.3737709 Y1 - 2025 UR - https://doi.org/10.1145/3709017.3737709 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-61584 SN - 979-8-4007-1413-9 SP - 43 EP - 51 PB - ACM CY - New York ER - TY - INPR A1 - Song, Rui A1 - Liang, Chenwei A1 - Xia, Yan A1 - Zimmer, Walter A1 - Cao, Hu A1 - Caesar, Holger A1 - Festag, Andreas A1 - Knoll, Alois T1 - CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving N2 - Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic environments presents significant challenges in accurately rendering these scenes. In this paper, we introduce a novel 4D Gaussian Splatting (4DGS) approach, which incorporates context and temporal deformation awareness to improve dynamic scene rendering. Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians, ensuring meaningful contextual embedding. Simultaneously, we track the temporal deformation of each Gaussian across adjacent frames. By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation within 3D space, facilitating a more precise representation of dynamic scenes. Experimental results show that our method improves 4DGS's ability to capture fine details in dynamic scene rendering for autonomous driving and outperforms other self-supervised methods in 4D reconstruction and novel view synthesis. Furthermore, CoDa-4DGS deforms semantic features with each Gaussian, enabling broader applications. UR - https://doi.org/10.48550/arXiv.2503.06744 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2503.06744 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58313 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Heinl, Patrizia A1 - Patapovas, Andrius A1 - Pilgermann, Michael T1 - Towards AI-enabled Cyber Threat Assessment in the Health Sector N2 - Cyber attacks on the healthcare industry can have tremendous consequences and the attack surface expands continuously. In order to handle the steadily rising workload, an expanding amount of analog processes in healthcare institutions is digitized. Despite regulations becoming stricter, not all existing infrastructure is sufficiently protected against cyber attacks. With an increasing number of devices and digital processes, the system and network landscape becomes more complex and harder to manage and therefore also more difficult to protect. The aim of this project is to introduce an AI-enabled platform that collects security relevant information from the outside of a health organization, analyzes it, delivers a risk score and supports decision makers in healthcare institutions to optimize investment choices for security measures. Therefore, an architecture of such a platform is designed, relevant information sources are identified, and AI methods for relevant data collection, selection, and risk scoring are explored. UR - https://doi.org/10.48550/arXiv.2409.12765 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2409.12765 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58381 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Barbosa da Silva, Leonardo A1 - Lobo, Silas A1 - Fernández, Evelio A1 - Facchi, Christian ED - Vinel, Alexey ED - Berns, Karsten ED - Ploeg, Jeroen ED - Gusikhin, Oleg T1 - What Is the Right Bounding Box of a VRU Cluster in V2X Communication? How to Form a Good Shape? T2 - Vehits 2024: 10th International Conference on Vehicle Technology and Intelligent Transport Systems Proceedings N2 - Among the possible traffic members on a Vehicle-to-Everything network, the term Vulnerable Road User (VRU) is assigned e.g. to pedestrians and cyclists. The VRU Awareness Message (VAM) is used by VRUs to inform other users of their presence and ensure they are perceived in a traffic system. Since the number of VRUs in crowded areas might be very high, the over-the-air traffic might be overloaded. To reduce channel overload, VAMs offer a clustering feature in which VRUs with similar kinematics and positions can group themselves so that only one device transmits messages. The VRU Basic Service specification describes the cluster as a bounding box that must cover all its members using a geometric shape so that other vehicles in the vicinity can avoid colliding with the contained VRUs. This paper contributes to the standardization effort by introducing a data structure, the Cluster Map, for the clustering in the VRU Basic Service. Furthermore, this work is the first to suggest strategies for forming bounding box shapes. Simulation results show that each of the geometry types is useful in different situations, thus further research on the topic is advised. UR - https://doi.org/10.5220/0012699100003702 Y1 - 2024 UR - https://doi.org/10.5220/0012699100003702 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48553 SN - 978-989-758-703-0 SP - 144 EP - 155 PB - SciTePress CY - Setúbal ER - TY - INPR A1 - Paula, Daniel A1 - Bauder, Maximilian A1 - Pfeilschifter, Claus A1 - Petermeier, Franziska A1 - Kubjatko, Tibor A1 - Böhm, Klaus A1 - Riener, Andreas A1 - Schweiger, Hans-Georg T1 - Impact of Partially Automated Driving Functions on Forensic Accident Reconstruction: A Simulator Study on Driver Reaction Behavior in the Event of a Malfunctioning System Behavior N2 - Partially automated driving functions (SAE Level 2) can control a vehicle's longitudinal and lateral movements. However, taking over the driving task involves automation risks that the driver must manage. In severe accidents, the driver's ability to avoid a collision must be assessed, considering their expected reaction behavior. The primary goal of this study is to generate essential data on driver reaction behavior in case of malfunctions in partially automated driving functions for use in legal affairs. A simulator study with two scenarios involving 32 subjects was conducted for this purpose. The first scenario investigated driver reactions to system limitations during cornering. The second scenario examined driver responses to phantom braking caused by the AEBS. As a result, the first scenario shows that none of the subjects could control the situation safely. Due to partial automation, we could also identify a new part of the reaction time, the hands-on time, which leads to increased steering reaction times of 1.18 to 1.74 seconds. In the second scenario, we found that 25 of the 32 subjects could not override the phantom braking by pressing the accelerator pedal, although 16 subjects were informed about the system analog to the actual vehicle manuals. Overall, the study suggests that the current legal perspective on vehicle control and the expected driver reaction behavior for accident avoidance should be reconsidered. UR - https://doi.org/10.20944/preprints202311.0947.v1 Y1 - 2023 UR - https://doi.org/10.20944/preprints202311.0947.v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-42173 PB - Preprints CY - Basel ER - TY - CHAP A1 - Eder, Lukas A1 - Löw, Jakob A1 - Hof, Hans-Joachim T1 - Charging Communication Sniffing and Man-in-the-Middle Attacks T2 - Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems N2 - In recent years an increasing amount of electric vehicle fast charging stations have been built to meet the growing demand from rising electric vehicle numbers. The standard for fast charging communication in europe is ISO 15118. In theory the standard includes security controls for authentication and transport encryption. In reality difficulties with implementing those security controls as well as insecure design within the standard lead to multiple possible attack vectors compromising the confidentiality and authenticity of charging communication sessions. The goal of this research is to present different approaches towards performing sniffing and man-in-the-middle attacks against charging communication. We also provide a novel approach, which does not rely on race conditions and thus is more reliable than previous approaches. UR - ttps://doi.org/10.1145/3679240.3734648 Y1 - 2025 UR - ttps://doi.org/10.1145/3679240.3734648 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60183 SN - 979-8-4007-1125-1 SP - 799 EP - 804 PB - ACM CY - New York ER - TY - CHAP A1 - Song, Rui A1 - Festag, Andreas A1 - Jagtap, Abhishek Dinkar A1 - Bialdyga, Maximilian A1 - Yan, Zhiran A1 - Otte, Maximilian A1 - Sadashivaiah, Sanath Tiptur A1 - Knoll, Alois T1 - First Mile: An Open Innovation Lab for Infrastructure-Assisted Cooperative Intelligent Transportation Systems T2 - 2024 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV55156.2024.10588500 Y1 - 2024 UR - https://doi.org/10.1109/IV55156.2024.10588500 SN - 979-8-3503-4881-1 SP - 1635 EP - 1642 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Hegde, Anupama A1 - Lobo, Silas A1 - Festag, Andreas T1 - Cellular-V2X for Vulnerable Road User Protection in Cooperative ITS T2 - 2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) UR - https://doi.org/10.1109/WiMob55322.2022.9941707 KW - Radio resource allocation in Cellular-V2X KW - VRU safety and protection KW - messaging services Y1 - 2022 UR - https://doi.org/10.1109/WiMob55322.2022.9941707 SN - 978-1-6654-6975-3 SP - 118 EP - 123 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Song, Rui A1 - Liu, Dai A1 - Chen, Dave Zhenyu A1 - Festag, Andreas A1 - Trinitis, Carsten A1 - Schulz, Martin A1 - Knoll, Alois T1 - Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments T2 - IJCNN 2023 Conference Proceedings UR - https://doi.org/10.1109/IJCNN54540.2023.10191879 Y1 - 2023 UR - https://doi.org/10.1109/IJCNN54540.2023.10191879 SN - 978-1-6654-8867-9 PB - IEEE CY - Piscataway ER -