Nektaria Kaloudi

• Kaloudi, Nektaria & Li, Jingyue (2025). The ML-based sensor data deception targeting cyber physical systems: A review. Computer Science Review. ISSN 1574-0137. 57. doi: 10.1016/j.cosrev.2025.100753. Full text in Research Archive Show summary

  The security of cyber–physical systems is crucial due to their critical applications. The increasing success of machine learning (ML) has raised growing concerns about its impact on the cybersecurity of cyber–physical systems. Although several studies have assessed the cybersecurity of cyber–physical systems, there remains a lack of systematic understanding of how ML techniques can contribute to the use of deception on these systems. In this study, we aim to systematize findings on the use of ML for sensor data deception in both attack and defense scenarios. We analyzed 13 offensive and 3 defensive approaches that leverage ML for sensor data deception targeting cyber–physical systems. We summarized the offensive and defensive sensor data deception implementations with impact on cyber–physical systems at the system level, and the mechanisms to defend offensive deception. Additionally, we provide key insights and outline challenges intended to guide future research on defending against ML-based cyber deception in cyber–physical systems.

• Jepsen, Louise Præstiin; Meland, Per Håkon & Kaloudi, Nektaria (2024). Increasing maritime cybersecurity awareness through game-based learning. Journal of Physics: Conference Series (JPCS). ISSN 1742-6588. 2867. doi: 10.1088/1742-6596/2867/1/012050. Full text in Research Archive Show summary

  Increased connectivity, digitalization and emerging autonomous operations within the maritime sector are paving the road for new cybersecurity risks. Such risks are not just a technical concern, as effective awareness and training programs play an important role in increasing the knowledge of relevant cyberattacks and defences, thereby improving security practices among stakeholders. Serious games have emerged as an engaging method to train individuals, effectively communicate an understanding of emerging cybersecurity threats and promote cybersecurity culture and hygiene. This paper delves into the development process of an asymmetrical strategy game for the maritime sector. The game uses a red versus blue paradigm to educate players about critical assets of maritime operations and how they can be exploited. The novelty of this work has been to design a gameplay based on actual incidents that for instance shipping companies have been facing up until today and likely future events. We employ a design science research methodology to ensure problem relevance and utility for practitioners. The game has been designed towards a demography of students from maritime education and training institutions and professionals working in the maritime sector but should be appealing to others looking to expand their comprehension of the maritime cybersecurity intricacies as well. The game serves as a pedagogical learning tool for elevating cybersecurity awareness, preparedness and response in the maritime digitalization sphere.

• Kaloudi, Nektaria & Li, Jingyue (2023). AST-SafeSec: Adaptive Stress Testing for Safety and Security Co-Analysis of Cyber-Physical Systems. IEEE Transactions on Information Forensics and Security. ISSN 1556-6013. 18, p. 5567–5579. doi: 10.1109/TIFS.2023.3309160. Full text in Research Archive Show summary

  Cyber-physical systems are becoming more intelligent with the adoption of heterogeneous sensor networks and machine learning capabilities that deal with an increasing amount of input data. While this complexity aims to solve problems in various domains, it adds new challenges for the system assurance. One issue is the rise in the number of abnormal behaviors that affect system performance due to possible sensor faults and attacks. The combination of safety risks, which are usually caused by random sensor faults and security risks that can happen during any random system state, makes the full coverage testing of the cyber-physical system challenging. Existing techniques are inadequate to deal with complex safety and security co-risks against cyber-physical systems. In this paper, we propose AST-SafeSec, an analysis methodology for both safety and security aspects that utilizes reinforcement learning to identify the most likely adversarial paths at various normal or failure states of a cyber-physical system that can influence system behavior through its sensor data. The methodology is evaluated using an autonomous vehicle scenario by incorporating a security attack into the stochastic sensor elements of a vehicle. Evaluation results show that the methodology analyzes the interaction of malicious attacks with random faults and identifies the incident caused by the interactions and the most likely path that leads to the incident.

• Kaloudi, Nektaria & Li, Jingyue (2021). Comparison of Risk Analysis Approaches for Analyzing Emergent Misbehavior in Autonomous Systems. In Castanier, Bruno; Cepin, Marko; Bigaud, David & Berenguer, Christophe (Ed.), Proceedings of the 31st European Safety and Reliability Conference. Research Publishing Services. ISSN 9789811820168. p. 383–390. doi: 10.3850/978-981-18-2016-8_213-cd. Full text in Research Archive
• Meyer, Torstein; Kaloudi, Nektaria & Li, Jingyue (2021). A Systematic Literature Review on Malicious Use of Reinforcement Learning. In Hauge, André Alexandersen (Eds.), Proceeding of the 2021 IEEE/ACM 2nd International Workshop on Engineering and Cybersecurity of Critical Systems (EnCyCriS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665445535. p. 21–28. doi: 10.1109/EnCyCriS52570.2021.00011. Full text in Research Archive
• Kaloudi, Nektaria & Li, Jingyue (2020). The AI-based cyber threat landscape: A survey. ACM Computing Surveys. ISSN 0360-0300. 53(1). doi: 10.1145/3372823. Full text in Research Archive Show summary

  Recent advancements in artificial intelligence (AI) technologies have induced tremendous growth in innovation and automation. Although these AI technologies offer significant benefits, they can be used maliciously. Highly targeted and evasive attacks in benign carrier applications, such as DeepLocker, have demonstrated the intentional use of AI for harmful purposes. Threat actors are constantly changing and improving their attack strategy with particular emphasis on the application of AI-driven techniques in the attack process, called AI-based cyber attack, which can be used in conjunction with conventional attack techniques to cause greater damage. Despite several studies on AI and security, researchers have not summarized AI-based cyber attacks enough to be able to understand the adversary’s actions and to develop proper defenses against such attacks. This study aims to explore existing studies of AI-based cyber attacks and to map them onto a proposed framework, providing insight into new threats. Our framework includes the classification of several aspects of malicious uses of AI during the cyber attack life cycle and provides a basis for their detection to predict future threats. We also explain how to apply this framework to analyze AI-based cyber attacks in a hypothetical scenario of a critical smart grid infrastructure.

• Li, Jingyue; Zhang, Jin & Kaloudi, Nektaria (2018). Could We Issue Driving Licenses to Autonomous Vehicles? Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 11094 LNCS, p. 473–480. doi: 10.1007/978-3-319-99229-7_41. Full text in Research Archive Show summary

  Many companies are studying autonomous vehicles. One trend in the development of control algorithms for autonomous vehicles is the use of deep-learning approaches. The general idea is to simulate a human driver’s decision-making and behavior in various scenarios without necessarily knowing why the decision is made. In this position paper, we first argue that traditional safety analysis methods need to be extended to verify deep-learning-based autonomous vehicles. Then, we propose borrowing ideas from the process of issuing driving licenses to human drivers to verify autonomous vehicles. Verification of autonomous vehicles could focus on sufficient training as well as mental and physical health checks. Based on this position, we list several challenges that need to be addressed.

View all works in NVA

• Kaloudi, Nektaria; Li, Jingyue; Katsikas, Sokratis & Johnsen, Stig Ole (2023). Understanding and Analyzing Emergent Misbehavior on Cyber-Physical Systems. Norges teknisk-naturvitenskapelige universitet. ISSN 9788232651962. Full text in Research Archive Show summary

  In a constantly evolving world, various technologies such as artificial intelligence (AI) influence the development of digital transformation through its decision-making capabilities. Cyber-physical systems (CPSs) are becoming more complex, and advanced adversaries are contriving new sophisticated ways to perpetrate their missions. Given the increased complexity of modern systems, cyber risks are getting more difficult to be handled, leading to an expansion of the attack surface. In response, there is a need to improve their safety and security, which are of the utmost importance. The challenges are twofold: (i) advances in CPSs; and (ii) evolving cyber threat landscape that entails new challenges for risk identification. On the one hand, CPSs are likely to exhibit emergent behaviors, considering the system as a whole, success and failure are increasingly understood as emergent rather than resultant. On the other hand, attack strategies are constantly evolving that affect CPSs, especially when AI can be used as a malicious tool by adversaries, which makes the situation even more challenging. Therefore, sufficient understanding and analysis of potential risks to support relevant operations should be at the forefront to ensure a safe transition to a connected world. This thesis aims to provide knowledge on the investigation of emergent misbehavior in the context of CPS, with a focus on the reciprocal influence of AI on cyberthreat behaviors. It develops new knowledge, methods, and guidance that provide the set of processes and practices to identify potential risks, as well as suggestions to address them. The thesis provides systematic studies on four sets of aspects:1) investigation of emergent risk concept; 2) new knowledge and a framework for mapping AI offensive capabilities; 3) new knowledge and a taxonomy of machine learning (ML)-based sensor data deception approaches as a particular type of ML-based attack strategy, which targets the sensor data of CPS; and 4) a methodology for safety and security co-analysis targeting CPS to address the ML-based sensor data deception risk. The resulting contributions provide an improved understanding of the changing threats and risks, as well as propose ways for preventing undesirable emergent misbehaviors on CPS. Finally, this thesis discusses research and practical implications and sheds light on avenues for future research.

View all works in NVA