Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions

Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario, where anomaly detectors continuously monitor inter-agent communications and block detected adversarial messages. Although existing attacks are effective without discussion monitoring, we show that they exhibit detectable patterns and largely fail under such monitoring constraints. But does this imply that monitoring alone is sufficient to secure multi-agent discussions? To answer this question, we develop a novel attack method explicitly tailored to the discussion-monitored scenario. Extensive experiments demonstrate that effective attacks remain possible even under continuous monitoring, indicating that monitoring alone does not eliminate adversarial risks.

Key Contributions

Identifies and formalizes the 'discussion-monitored scenario' where anomaly detectors continuously monitor multi-agent communications
Demonstrates that existing multi-agent attacks fail under continuous monitoring (>93.5% detection rate)
Develops novel stealth attack method tailored to evade anomaly detection while maintaining attack effectiveness in monitored multi-agent discussions