8 papers
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
Weidi Luo, Qiming Zhang, Yihao Quan +5
Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn in…
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
Weidi Luo, Xiaofei Wen, Tenghao Huang +5
Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain…
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Weidi Luo, Tianyu Lu, Qiming Zhang +8
Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models enable impressive reasoning cap…
Your Harness is Not Secure: Benchmarking Real-world Threat of Command Line Interface Agent
Weidi Luo, Qiming Zhang, Tianyu Lu +9
Command-line interface (CLI) agents powered by large language models (LLMs) can interpret natural-language requests, plan multi-step tasks, execute shell commands, and modify files…
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
Haoran Lu, Luyang Fang, Ruidong Zhang +47
Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment…
Disentangling Memory and Reasoning Ability in Large Language Models
Mingyu Jin, Weidi Luo, Sitao Cheng +5
Large Language Models (LLMs) have demonstrated strong performance in handling complex tasks requiring both extensive knowledge and reasoning abilities. However, the existing LLM in…