Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information between agents and their interaction with external environments, such as LLM, tools, and users, inevitably introduces significant risks of sensitive data leakage, including vulnerabilities to attacks such as eavesdropping and prompt injection. Existing MACS lack fine-grained data protection controls, making it challenging to manage sensitive information securely. In this paper, we take the first step to mitigate the MACS's data leakage threat through a privacy-enhanced MACS development paradigm, Maris. Maris enables rigorous message flow control within MACS by embedding reference monitors into key multi-agent conversation components. We implemented Maris as an integral part of widely-adopted open-source multi-agent development frameworks, AutoGen and LangChain. To evaluate its effectiveness, we develop a Privacy Assessment Framework that emulates MACS under different threat scenarios. Our evaluation shows that Maris effectively mitigated sensitive data leakage threats across three different task suites while maintaining a high task success rate.

翻译：基于大语言模型（LLM）的多智能体协作系统（MACS）通过利用各智能体的专业化能力及智能体间的通信，高效解决复杂问题。然而，智能体之间固有的信息交换及其与外部环境（如LLM、工具和用户）的交互，不可避免地引入了敏感数据泄露的重大风险，包括易受窃听和提示注入等攻击的漏洞。现有MACS缺乏细粒度的数据保护控制机制，难以安全地管理敏感信息。本文率先提出了一种隐私增强型MACS开发范式Maris，以缓解MACS的数据泄露威胁。Maris通过将引用监视器嵌入多智能体对话的关键组件，实现了MACS内严格的消息流控制。我们已在广泛采用的开源多智能体开发框架AutoGen和LangChain中实现了Maris作为其核心组成部分。为评估其有效性，我们开发了一个隐私评估框架，该框架可模拟不同威胁场景下的MACS。评估结果表明，Maris在三个不同任务套件中有效缓解了敏感数据泄露威胁，同时保持了较高的任务成功率。