arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.08460cs.CRcs.AI
收藏

当子代理继承:在多代理网络中建模和利用子代理生成

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks

University of Louisiana at Lafayette(路易斯安那州立大学拉弗奈分校)

Ziwen Cai, Yihe Zhang, Xiali Hei

AI总结:

本文研究多代理网络中子代理继承带来的安全风险,指出继承内存可能传播恶意指令,提出通过显式安全不变量进行防御。

摘要:

自2022年ChatGPT发布以来,大型语言模型(LLMs)迅速从聊天机器人界面发展为能够通过工具和新生成的子代理进行任务委托的代理系统。尽管这些能力提升了自动化和可扩展性,但也为多代理网络带来了新的安全风险。现有研究探讨了个体LLM代理如何通过提示注入、 jailbreaking、毒化检索数据或恶意扩展被攻破。较少研究关注的是当一个代理在多代理网络中被攻破后会发生什么。特别是,继承自父代理的记忆可能将恶意指令、过时状态或意外行为规则带入新生成的子代理,使局部攻击能够跨代理边界扩散。本文通过子代理继承的视角建模现代多代理网络,分析发现当前框架可通过不安全的记忆继承、弱资源控制、过时的生成后状态和不当的终止权限违反信任边界。我们在实际代理框架中展示了这些风险,并基于显式安全不变量提出防御措施。我们的发现表明,继承不仅是实现细节,而是影响多代理系统安全性的核心组件。

英文摘要:

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities improve automation and scalability, they also pose new security risks in multi-agent networks. Existing research has studied how individual LLM-based agents can be compromised through prompt injection, jailbreaking, poisoned retrieval data, or malicious extensions. Less is known about what happens after one agent is compromised inside a multi-agent network. In particular, inherited memory from parent agents can carry malicious instructions, outdated states, or unintended behavioral rules into newly created subagents, allowing a local compromise to spread across agent boundaries. In this paper, we model contemporary multi-agent networks through the lens of subagent inheritance. Our analysis shows that current frameworks can violate trust boundaries through insecure memory inheritance, weak resource control, stale post-spawn state, and improper termination authority. We demonstrate these risks in real agent frameworks and propose defenses based on explicit security invariants. Our findings show that inheritance is not merely an implementation detail, but a central component influencing the security of multi-agent systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑