Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies

Ruixiao Lin, Xinhao Deng, Qingming Li +12

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Xinhao Deng, Yixiang Zhang, Jiaqing Wu +15

Provable Fairness Repair for Deep Neural Networks

Jianan Ma, Jingyi Wang, Qi Xuan +1

Patch Synthesis for Property Repair of Deep Neural Networks

Zhiming Chi, Jianan Ma, Pengfei Yang +4

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

Yunhao Feng, Ruixiao Lin, Ming Wen +12

Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement

Jianan Ma, Jingyi Wang, Qi Xuan +1

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Mingxiao Liu, Yitong Li, Haoren Zhao +6

The paper studies stealthy audio prompt injection attacks that hide malicious instructions within normal speech to hijack multimodal LLM agents, introduces a benchmark (AudioAgentS…

ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents

Jianan Ma, Xiaohu Du, Ruixiao Lin +9