通过反向传播计算节点贡献，动态识别并隔离恶意智能体。
Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
- 将多智能体通信建模为带符号有向无环图，用反向传播评估各智能体贡献。
- 在复杂动态环境中，对恶意智能体的识别准确率显著优于现有方法。
- 适合需要高可信度协作的大型语言模型应用，如安全决策系统。
多智能体系统（MAS）已成为大语言模型应用的主流范式。然而，复杂的多智能体设计引入了独特的可信性问题：攻击者可注入误导信息，通过系统传播感染良性智能体，导致错误输出。现有基于图的防御方法将智能体视为节点、通信视为边，但仅限于静态图防御。本文提出一种动态防御范式，将MAS通信建模为带符号有向无环图，并通过反向传播计算每个智能体对最终决策的贡献，从而精准识别并隔离恶意智能体，保障多智能体任务协作的安全性。在复杂动态的MAS环境中的实验表明，该方法显著优于现有防御机制，为可信的MAS部署提供了有效防护。代码已开源：https://github.com/ChengcanWu/BPD。
原文摘要 · Abstract (English)
Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthiness concerns: adversarial agents can inject misleading information that propagates contagiously through the system, corrupting benign agents and leading to false outputs. Existing graph-based defenses model agents as nodes and communications as edges, yet are limited to static-graph defenses. In this paper, we propose a dynamic defense paradigm that models MAS communication as a signed directed acyclic graph and computes each agent's contribution to the final decision via backward propagation, enabling accurate identification and isolation of malicious agents to secure multi-agent task collaboration. Experimental results in complex and dynamic MAS environments demonstrate that our method notably outperforms existing MAS defense mechanisms, providing an effective guardrail for trustworthy MAS deployment. Our code is available at https://github.com/ChengcanWu/BPD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。