Related papers: RTAEval: A framework for evaluating runtime assura…
Current validation methods often rely on recorded data and basic functional checks, which may not be sufficient to encompass the scenarios an autonomous vehicle might encounter. In addition, there is a growing need for complex scenarios…
With the rising number of IoT devices, the security of such devices becomes increasingly important. Remote attestation (RA) is a distinct security service that allows a remote verifer to reason about the state of an untrusted remote prover…
As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning…
Remote attestation (RA) is a popular means of detecting malware in embedded and IoT devices. RA is usually realized as an interactive protocol, whereby a trusted party -- verifier -- measures integrity of a potentially compromised remote…
In the coming years, usage of Unmanned Aerial Vehicles (UAVs) is expected to grow tremendously. Maintaining security of UAVs under cyber attacks is an important yet challenging task, as these attacks are often erratic and difficult to…
Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially…
A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise due to the uncertain environment in which AVs operate such as road and weather conditions, errors in…
As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional…
Systems Theoretic Process Analysis (STPA) is a widely recommended method for analysing complex system safety. STPA can identify numerous Unsafe Control Actions (UCAs) and requirements depending on the level of granularity of the analysis…
We present an approach for verifying systems at runtime. Our approach targets distributed systems whose components communicate with monitors over unreliable channels, where messages can be delayed, reordered, or even lost. Furthermore, our…
Timed automata (TA) is used for modeling systems with timing aspects. A TA extends a finite automaton with a set of real valued variables called clocks, that measure the time and constraints over the clocks guard the transitions. A…
Challenges related to automated driving are no longer focused on just the construction of such automated vehicles (AVs), but in assuring the safety of their operation. Recent advances in Level 3 and Level 4 autonomous driving have motivated…
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…
We present a hierarchical safe auto-taxiing framework to enhance the automated ground operations of multiple unmanned aircraft systems (multi-UAS). The auto-taxiing problem becomes particularly challenging due to (i) unknown disturbances,…
Cybersecurity demands rigorous and scalable techniques to ensure system correctness, robustness, and resilience against evolving threats. Automated reasoning, encompassing formal logic, theorem proving, model checking, and symbolic…
The excitement brought by the development of AI agents came alongside arising problems. These concerns centered around users' trust issues towards AIs, the risks involved, and the difficulty of attributing responsibilities and liabilities.…
Testing autonomous vehicles (AVs) requires complex oracles to determine if the AVs behavior conforms with specifications and humans' expectations. Available open source oracles are tightly embedded in the AV simulation software and are…
Due to the high flexibility and versatility, unmanned aerial vehicles (UAVs) are leveraged in various fields including surveillance and disaster rescue.However, in UAV networks, routing is vulnerable to malicious damage due to distributed…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Ensuring the runtime safety of autonomous systems remains challenging due to deep learning components' inherent uncertainty and their sensitivity to environmental changes. In this paper, we propose an enhancement of traditional uncertainty…