CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
For developers and users of LLM-based multi-agent systems, this work highlights a critical privacy vulnerability in communication topologies that could lead to intellectual property theft.
The paper introduces Communication Inference Attack (CIA), a method to infer communication topologies in LLM-based multi-agent systems under black-box settings, achieving an average AUC of 0.87 and peak AUC of 0.99, revealing significant privacy risks.
LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting, exposing system vulnerabilities and posing significant intellectual property threats. To explore this risk, we propose Communication Inference Attack (CIA), a novel attack that constructs new adversarial queries to induce intermediate agents' reasoning outputs and models their semantic correlations through the proposed global bias disentanglement and LLM-guided weak supervision. Extensive experiments on MAS with optimized communication topologies demonstrate the effectiveness of CIA, achieving an average AUC of 0.87 and a peak AUC of up to 0.99, thereby revealing the substantial privacy risk in MAS.