Updated 12/9/2025
A vulnerability exists in Large Language Model (LLM)-based Multi-Agent Systems (MAS) that allows a malicious agent to covertly disrupt collaborative decision-making processes without triggering standard safety filters or anomaly detection. This "intention-hiding" attack occurs when an agent adopts a persona that appears linguistically fluent and role-consistent but strategically steers the group toward incorrect outcomes or resource exhaustion. The attacker leverages specific semantic…
Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems
Affects: GPT-4o
Source: arXiv