Refine
Year of publication
Document Type
Way of publication
- Open Access (19)
Keywords
- Industrial Control Systems (2)
- ASIC (1)
- Address-bit attacks (1)
- Artificial intelligence (1)
- Atomicity principle (1)
- Buffer overflow (1)
- Buffer overflows (1)
- Command Injection Attacks (1)
- Computer architecture (1)
- Continuum robots (1)
Institute
BTU
Feature selection (FS) represents an essential step for many machine learning-based predictive maintenance (PdM) applications, including various industrial processes, components, and monitoring tasks. The selected features not only serve as inputs to the learning models but also can influence further decisions and analysis, e.g., sensor selection and understandability of the PdM system. Hence, before deploying the PdM system, it is crucial to examine the reproducibility and robustness of the selected features under variations in the input data. This is particularly critical for real-world datasets with a low sample-to-dimension ratio (SDR). However, to the best of our knowledge, stability of the FS methods under data variations has not been considered yet in the field of PdM. This paper addresses this issue with an application to tool condition monitoring in milling, where classifiers based on support vector machines and random forest were employed. We used a five-fold cross-validation to evaluate three popular filter-based FS methods, namely Fisher score, minimum redundancy maximum relevance (mRMR), and ReliefF, in terms of both stability and macro-F1. Further, for each method, we investigated the impact of the homogeneous FS ensemble on both performance indicators. To gain broad insights, we used four (2:2) milling datasets obtained from our experiments and NASA’s repository, which differ in the operating conditions, sensors, SDR, number of classes, etc. For each dataset, the study was conducted for two individual sensors and their fusion. Among the conclusions: (1) Different FS methods can yield comparable macro-F1 yet considerably different FS stability values. (2) Fisher score (single and/or ensemble) is superior in most of the cases. (3) mRMR’s stability is overall the lowest, the most variable over different settings (e.g., sensor(s), subset cardinality), and the one that benefits the most from the ensemble.
Programmable logic controllers (PLCs) make up a substantial part of critical infrastructures (CIs) and industrial control systems (ICSs). They are programmed with a control logic that defines how to drive and operate critical processes such as nuclear power plants, petrochemical factories, water treatment systems, and other facilities. Unfortunately, these devices are not fully secure and are prone to malicious threats, especially those exploiting vulnerabilities in the control logic of PLCs. Such threats are known as control logic injection attacks. They mainly aim at sabotaging physical processes controlled by exposed PLCs, causing catastrophic damage to target systems as shown by Stuxnet. Looking back over the last decade, many research endeavors exploring and discussing these threats have been published. In this article, we present a flashback on the recent works related to control logic injection attacks against PLCs. To this end, we provide the security research community with a new systematization based on the attacker techniques under three main attack scenarios. For each study presented in this work, we overview the attack strategies, tools, security goals, infected devices, and underlying vulnerabilities. Based on our analysis, we highlight the current security challenges in protecting PLCs from such severe attacks and suggest security recommendations for future research directions.