Yizhe Xie

Yizhe Xie, Congcong Zhu, Xinyue Zhang et al.

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach raises the defense success rate from a baseline of 0.32 to over 0.89 and significantly mitigates the cascading spread of minor errors.

Yizhe Xie, Congcong Zhu, Xinyue Zhang et al.

Multi-agent systems powered by Large Language Models (LLM-MAS) have demonstrated remarkable capabilities in collaborative problem-solving. However, their deployment also introduces new security risks. Existing research on LLM-based agents has primarily examined single-agent scenarios, while the security of multi-agent systems remains largely unexplored. To address this gap, we present a systematic study of intention-hiding threats in LLM-MAS. We design four representative attack paradigms that subtly disrupt task completion while maintaining a high degree of stealth, and evaluate them under centralized, decentralized, and layered communication structures. Experimental results show that these attacks are highly disruptive and can easily evade existing defense mechanisms. To counter these threats, we propose AgentXposed, a psychology-inspired detection framework. AgentXposed draws on the HEXACO personality model, which characterizes agents through psychological trait dimensions, and the Reid interrogation technique, a structured method for eliciting concealed intentions. By combining progressive questionnaire probing with behavior-based inter-agent monitoring, the framework enables the proactive identification of malicious agents before harmful actions are carried out. Extensive experiments across six datasets against both our proposed attacks and two baseline threats demonstrate that AgentXposed effectively detects diverse forms of malicious behavior, achieving strong robustness across multiple communication settings.