Related papers: Measuring Safety Alignment Effects in Autonomous S…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

The deployment of large language models (LLMs) in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused…

As teachers increasingly turn to GenAI in their educational practice, we need robust methods to benchmark large language models (LLMs) for pedagogical purposes. This article presents an embedding-based benchmarking framework to detect bias…

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against diverse adversarial attack vectors. We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack…

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correctness. However,…

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings,…

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

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…

Safe fine-tuning defenses are often endorsed on the basis of a held-out gap reduction, but the same reduction can come from sampling noise, subject artifacts, capability loss, or a mechanism that does not transfer. We introduce Acceptance…

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

We investigate how large language models (LLMs) fail when operating as autonomous agents with tool-use capabilities. Using the Kamiwaza Agentic Merit Index (KAMI) v0.1 benchmark, we analyze 900 execution traces from three representative…

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Hacking poses a significant threat to cybersecurity, inflicting billions of dollars in damages annually. To mitigate these risks, ethical hacking, or penetration testing, is employed to identify vulnerabilities in systems and networks.…