12 papers
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Lingqi Jiang, Jialuo Chen, Jianan Ma +8
Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and inspect durin…
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills
Mingxiao Liu, Zhoumian Jiang, Jianan Ma +4
Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the e…
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Jialuo Chen, Lingqi Jiang, Xinhao Deng +7
Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a…
SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
Jialuo Chen, Minghe Wang, Lingqi Jiang +7
LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workfl…
Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents
Mingxiao Liu, Yitong Li, Haoren Zhao +6
Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction…
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
Yunhao Feng, Ruixiao Lin, Ming Wen +12
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa…
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin, Xinhao Deng, Qingming Li +12
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversa…
Provable Fairness Repair for Deep Neural Networks
Jianan Ma, Jingyi Wang, Qi Xuan +1
Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In response, extensive NN repair techniques have been developed to adjust models an…
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents
Jianan Ma, Xiaohu Du, Ruixiao Lin +9
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Existing L…
Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
Xinhao Deng, Yixiang Zhang, Jiaqing Wu +15
Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled…
Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement
Jianan Ma, Jingyi Wang, Qi Xuan +1
It is known that deep neural networks may exhibit dangerous behaviors under various security threats (e.g., backdoor attacks, adversarial attacks and safety property violation) and…
Patch Synthesis for Property Repair of Deep Neural Networks
Zhiming Chi, Jianan Ma, Pengfei Yang +4
Deep neural networks (DNNs) are prone to various dependability issues, such as adversarial attacks, which hinder their adoption in safety-critical domains. Recently, NN repair tech…