Activation-space divergence detects and corrects compromised LLM agents in multi-agent systems without interaction graphs or synchronized rounds, outperforming graph baselines especially under async stealthy attacks.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
citing papers explorer
-
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Activation-space divergence detects and corrects compromised LLM agents in multi-agent systems without interaction graphs or synchronized rounds, outperforming graph baselines especially under async stealthy attacks.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.