3 citations · 3 across the 12 of their papers we have counts for
7 papers · 1 filter
Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents
Haoyu Wang, Wei Zhao, Yedi Zhang +2
Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation. We show t…
: Improving Agent Safety through Multi-Stage Defense
Zibo Xiao, Haoyu Wang, Jun Sun
Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may e…
Position: AI Safety Requires Effective Controllability
Yige Li, Yunhao Feng, Jun Sun
AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of m…
SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
Haoyu Wang, Zibo Xiao, Yedi Zhang +2
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the pot…
LLM-enabled Applications Require System-Level Threat Monitoring
Yedi Zhang, Haoyu Wang, Xianglin Yang +2
LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, h…
ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing
Jianlei Chi, Yuzhen Wu, Jiaxuan Hou +7
Automated Driving System (ADS) acts as the brain of autonomous vehicles, responsible for their safety and efficiency. Safe deployment requires thorough testing in diverse real-worl…
AIR: Improving Agent Safety through Incident Response
Zibo Xiao, Jun Sun, Junjie Chen
Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost ex…