Related papers: Grammar-Constrained Refinement of Safety Operation…
In the last decades, Cyber-physical Systems (CPSs) have experienced a significant technological evolution and increased connectivity, at the cost of greater exposure to cyber-attacks. Since many CPS are used in safety-critical systems, such…
Cyber-Physical Systems (CPSs) are often safety-critical and deployed in uncertain environments. Identifying scenarios where CPSs do not comply with requirements is fundamental but difficult due to the multidisciplinary nature of CPSs. We…
Cyber-Physical Production Systems (CPPS) are long-living and mechatronic systems, which include mechanics, electrics/electronics and software. The interdisciplinary nature combined with challenges and trends in the context of Industry 4.0…
Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…
Autonomous Robotics Systems are inherently safety-critical and have complex safety issues to consider (for example, a safety failure can lead to a safety failure). Before they are deployed, these systems of have to show evidence that they…
Test automation requires automated oracles to assess test outputs. For cyber physical systems (CPS), oracles, in addition to be automated, should ensure some key objectives: (i) they should check test outputs in an online manner to stop…
Formal language techniques have been used in the past to study autonomous dynamical systems. However, for controlled systems, new features are needed to distinguish between information generated by the system and input control. We show how…
Safety-aligned LLMs remain vulnerable to digital phenomena like textese that introduce non-canonical perturbations to words but preserve the phonetics. We introduce CMP-RT (code-mixed phonetic perturbations for red-teaming), a novel…
Software is now ubiquitous and involved in complex interactions with the human users and the physical world in so-called cyber-physical systems where the management of time is a major issue. Separation of concerns is a key asset in the…
Large Language Models (LLMs) have quickly risen to prominence due to their ability to perform at or close to the state-of-the-art in a variety of fields while handling natural language. An important field of research is the application of…
We consider the problem of controller design for linear time-invariant cyber-physical systems (CPSs) controlled via networks. Specifically, we adopt the set-up that a controller has already been designed to stabilize the plant. However, the…
Autonomous robots navigating in changing environments demand adaptive navigation strategies for safe long-term operation. While many modern control paradigms offer theoretical guarantees, they often assume known extrinsic safety…
Cyber-physical systems (CPS) are required to satisfy safety constraints in various application domains such as robotics, industrial manufacturing systems, and power systems. Faults and cyber attacks have been shown to cause safety…
Large language models (LLMs) have been used in many application domains, including cyber security. The application of LLMs in the cyber security domain presents significant opportunities, such as for enhancing threat analysis and malware…
Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive…
Cyber Physical Systems (CPS) are becoming ubiquitous and affect the physical world, yet security is seldom at the forefront of their design. This is especially true of robotic control algorithms which seldom consider the effect of a cyber…
The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…
Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during…
We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…
Failures in safety-critical Cyber-Physical Systems (CPS), both software and hardware-related, can lead to severe incidents impacting physical infrastructure or even harming humans. As a result, extensive simulations and field tests need to…