Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback
Pengyu Zhu, Jingyi Yang, Yi Liu +2
Agent skills package instructions, executable code, and task-specific resources into reusable artifacts that agents can improve using execution feedback. The same mechanism also en…
cs.CR2025
Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems
Pengyu Zhu, Lijun Li, Yaxing Lyu +3
LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. Howeve…
cs.CR2025
DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang +3
As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety v…