3 papers
cs.CR2026
Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
Yan Wang, Zhihao Zhang, Ke Chen +5
LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabilities and, once installed, can…
cs.CR2026
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Haowen Xu, Xue Tan, Lei Ma +6
While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction l…
cs.CR2024
HuntFUZZ: Enhancing Error Handling Testing through Clustering Based Fuzzing
Jin Wei, Ping Chen, Jun Dai +4
Testing a program's capability to effectively handling errors is a significant challenge, given that program errors are relatively uncommon. To solve this, Software Fault Injection…