相关论文: Grounds for Suspicion: Physics-based Early Warning…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

We consider the problem of false data injection attacks modeled as additive disturbances in various parts of a general LTI feedback system and derive necessary and sufficient conditions for the existence of stealthy unbounded attacks. We…

Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of…

Attacks in cyber-physical systems (CPS) which manipulate sensor readings can cause enormous physical damage if undetected. Detection of attacks on sensors is crucial to mitigate this issue. We study supervised regression as a means to…

In big data systems, the infrastructure is such that large amounts of data are hosted away from the users. In such a system information security is considered as a major challenge. From a customer perspective, one of the big risks in…

State estimation estimates the system condition in real-time and provides a base case for other energy management system (EMS) applications including real-time contingency analysis and security-constrained economic dispatch. Recent work in…

Motion planning under sensing uncertainty is critical for robots in unstructured environments to guarantee safety for both the robot and any nearby humans. Most work on planning under uncertainty does not scale to high-dimensional robots…

This study establishes a connection between the output-to-output gain (OOG), a sensitivity metric quantifying the impact of stealthy attacks, and a novel input-to-input gain (IIG) introduced to evaluate fault sensitivity under disturbances,…

Hardware Trojans are malicious modifications in digital designs that can be inserted by untrusted supply chain entities. Hardware Trojans can give rise to diverse attack vectors such as information leakage (e.g. MOLES Trojan) and…

Dynamic systems in AI are often complex and heterogeneous, so that an internal specification is not accessible and verification techniques such as model checking are not applicable. Monitoring is in such cases an attractive alternative, as…

Stochastic dynamical systems have emerged as fundamental models across numerous application domains, providing powerful mathematical representations for capturing uncertain system behavior. In this paper, we address the problem of runtime…

Networks are difficult to configure correctly, and tricky to debug. These problems are accentuated by temporal and stateful behavior. Static verification, while useful, is ineffectual for detecting behavioral deviations induced by hardware…

Safety Instrumented Systems (SIS) protect major hazard facilities, e.g. power plants, against catastrophic accidents. An SIS consists of hardware components and a controller software -- the ``program''. Current safety analyses of SIS'…

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Modern industrial systems face a growing threat from sophisticated cyberattacks that can cause significant operational disruptions. This work presents a novel methodology for identification of the most critical cyberattacks that may disrupt…

Cyberattacks targeting critical infrastructures, such as water treatment facilities, represent significant threats to public health, safety, and the environment. This paper introduces a systematic approach for modeling and assessing covert…

Catastrophic regime shifts in complex natural systems may be averted through advanced detection. Recent work has provided a proof-of-principle that many systems approaching a catastrophic transition may be identified through the lens of…

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Security vulnerability analysis of Integrated Circuits using conventional design-time validation and verification techniques (like simulations, emulations, etc.) is generally a computationally intensive task and incomplete by nature,…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…