Pei-Yang Li

Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems

Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected by a later agent or propagated into a consequential task decision. Measuring local exploitability alone leaves this difference unresolved and provides li...

Reducing False Positives in Provenance-Based Intrusion Detection Systems

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

This work develops a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective, and proposes HARD (Harness-based Autonomous Runtime Defense Evolution),...