Related papers: Grammar-Constrained Refinement of Safety Operation…

Large language models (LLMs) allow users to query databases using natural language by translating questions into executable queries. Despite strong progress on tasks such as Text2SQL, Text2SPARQL, and Text2Cypher, most existing methods…

The rapid advancement of machine learning (ML) has led to its increasing integration into cyber-physical systems (CPS) across diverse domains. While CPS offer powerful capabilities, incorporating ML components introduces significant safety…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

The development of cyber-physical system (CPS) is a big challenge because of its complexity and its complex requirements. Especially in Requirements Engineering (RE), there exist many redundant and conflict requirements. Eliminating…

Human-robot collaboration in industrial settings requires precise and reliable communication to enhance operational efficiency. While Large Language Models (LLMs) understand general language, they often lack the domain-specific rigidity…

The analysis of cyber-physical systems (CPS) is challenging due to the large state space and the continuous changes occurring in their constituent parts. Design practices favor modularity to help reducing this complexity. In a previous…

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

In the current control design of safety-critical autonomous systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However,…

Cyber-physical systems (CPS), such as automotive systems, are starting to include sophisticated machine learning (ML) components. Their correctness, therefore, depends on properties of the inner ML modules. While learning algorithms aim to…

Insecure default values in software settings can be exploited by attackers to compromise the system that runs the software. As a countermeasure, there exist security-configuration guides specifying in detail which values are secure.…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to verify if code implementation satisfy…

Perception components in autonomous systems are often developed and optimized independently of downstream decision-making and control components, relying on established performance metrics like accuracy, precision, and recall. Traditional…

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Cyber-Physical Systems (CPS) are systems controlled by one or more computer-based components tightly integrated with a set of physical components, typically described as sensors and actuators, that can either be directly attached to the…

Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human feedback to address…

While the emergence of powerful language models along with Chain-of-thought prompting has made automation more and more omnipresent, it sometimes demonstrates its weakness in long-term or multi-step logical reasoning. For example, users…

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is…

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…