Related papers: Evaluating Implicit Regulatory Compliance in LLM T…

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public…

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…

As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge…

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…

Large language model agents for data analysis typically generate and execute code directly on databases. However, when applied to sensitive data, this approach poses significant security risks. To address this issue, we propose a…

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

Large Language Models (LLMs) have the potential to enhance Agent-Based Modeling by better representing complex interdependent cybersecurity systems, improving cybersecurity threat modeling and risk management. However, evaluating LLMs in…

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing…

As large language models (LLMs) rapidly evolve, they bring significant conveniences to our work and daily lives, but also introduce considerable safety risks. These models can generate texts with social biases or unethical content, and…

In many safety-critical engineering domains, hazard analysis techniques are an essential part of requirement elicitation. Of the methods proposed for this task, STPA (System-Theoretic Process Analysis) represents a relatively recent…

Large Language Models (LLMs) are increasingly being used to automate programming tasks. Yet, LLMs' capabilities in reasoning about program semantics are still inadequately studied, leaving significant potential for further exploration. This…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code.…

Safety verification of dynamical systems via barrier certificates is essential for ensuring correctness in autonomous applications. Synthesizing these certificates involves discovering mathematical functions with current methods suffering…

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks primarily assess functional correctness and neglect broader…

As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained on text corpora reliably reason about complex physics while adhering to safety…