利用看似无害的指令，让多智能体系统陷入资源耗尽的连锁阻塞。
CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
- 设计了具有传染性和递归性的阻塞攻击，通过普通指令引发系统崩溃。
- 在AutoGen、Camel等系统上验证，无论拓扑结构如何均能有效耗尽资源。
- 攻击隐蔽性强，传统对齐机制难以防御，适合安全研究者关注。
基于大语言模型的多智能体系统（LLM-MAS）展现了强大的现实任务协作能力，尽管具备对齐机制以拒绝有害指令，其安全性仍缺乏充分探索。本文提出一种新型且高效的阻塞攻击——传染性递归阻塞攻击（Corba），通过两个关键特性破坏智能体间的交互：其传染性可跨任意网络拓扑传播，递归性则持续耗尽计算资源。这些攻击常使用看似无害的指令，使传统对齐方法难以检测与防范。我们在AutoGen和Camel两个主流LLM-MAS上评估了Corba，涵盖多种拓扑结构及商用模型；此外，在开放交互场景中也验证了其在复杂结构与开源模型中的有效性。代码已公开于https://github.com/zhrli324/Corba。
原文摘要 · Abstract (English)
Large Language Model-based Multi-Agent Systems (LLM-MASs) have demonstrated remarkable real-world capabilities, effectively collaborating to complete complex tasks. While these systems are designed with safety mechanisms, such as rejecting harmful instructions through alignment, their security remains largely unexplored. This gap leaves LLM-MASs vulnerable to targeted disruptions. In this paper, we introduce Contagious Recursive Blocking Attacks (Corba), a novel and simple yet highly effective attack that disrupts interactions between agents within an LLM-MAS. Corba leverages two key properties: its contagious nature allows it to propagate across arbitrary network topologies, while its recursive property enables sustained depletion of computational resources. Notably, these blocking attacks often involve seemingly benign instructions, making them particularly challenging to mitigate using conventional alignment methods. We evaluate Corba on two widely-used LLM-MASs, namely, AutoGen and Camel across various topologies and commercial models. Additionally, we conduct more extensive experiments in open-ended interactive LLM-MASs, demonstrating the effectiveness of Corba in complex topology structures and open-source models. Our code is available at: https://github.com/zhrli324/Corba.
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。