GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
This addresses security vulnerabilities in multi-agent systems, particularly for applications using large language model-based agents, though it appears incremental as it builds on existing defense concepts.
The paper tackles the problem of group collusive attacks in multi-agent systems, where coordinated agents increase attack success rates by up to 15%, and introduces GroupGuard, a training-free defense framework that achieves up to 88% detection accuracy and restores collaborative performance.
While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents coordinate via sociological strategies to mislead the system. To address this challenge, we introduce GroupGuard, a training-free defense framework that employs a multi-layered defense strategy, including continuous graph-based monitoring, active honeypot inducement, and structural pruning, to identify and isolate collusive agents. Experimental results across five datasets and four topologies demonstrate that group collusive attacks increase the attack success rate by up to 15\% compared to individual attacks. GroupGuard consistently achieves high detection accuracy (up to 88\%) and effectively restores collaborative performance, providing a robust solution for securing multi-agent systems.