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 2604.18231cs.CRcs.OS
收藏

AgenTEE: 在边缘设备上实现保密大语言模型代理执行

AgenTEE: Confidential LLM Agent Execution on Edge Devices

Imperial College London(帝国理工学院);Dartmouth College(达特茅斯学院)

Sina Abdollahi, Mohammad M Maheri, Javad Forough, Amir Al Sadi, Josh Millar, David Kotz, Marios Kogias, Hamed Haddadi

AI总结:

本文提出AgenTEE系统,通过在边缘设备上部署保密虚拟机实现安全代理管道执行,降低延迟并保护隐私,实验显示其性能接近原生水平。

摘要:

大型语言模型(LLM)代理提供强大的自动化能力,但因其与非确定性模型和第三方服务的紧密集成,攻击面比传统应用更广。尽管当前部署主要依赖云服务,但新兴设计越来越多地在边缘设备上直接执行代理以减少延迟并增强隐私。然而,在边缘设备上安全地托管此类复杂代理管道仍然具有挑战性。这些部署必须保护专有资产(如系统提示和模型权重)和敏感的运行时状态,在易受软件攻击的异构平台上。为了解决这些挑战,我们提出了AgenTEE,一个在边缘设备上部署保密代理管道的系统。AgenTEE将代理运行时、推理引擎和第三方应用程序置于独立认证的保密虚拟机(cVM)中,并通过明确、可验证的通信通道调解其交互。基于Arm保密计算架构(CCA),一种近期扩展到Arm平台的扩展,AgenTEE强制对敏感资产和运行时状态进行强系统级隔离。我们的评估显示,这种多cVM系统是可行的,其性能接近原生水平,与商用操作系统多进程部署相比,运行时开销低于5.15%。

英文摘要:

Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and third-party services. While current deployments primarily rely on cloud-hosted services, emerging designs increasingly execute agents directly on edge devices to reduce latency and enhance user privacy. However, securely hosting such complex agent pipelines on edge devices remains challenging. These deployments must protect proprietary assets (e.g., system prompts and model weights) and sensitive runtime state on heterogeneous platforms that are vulnerable to software attacks and potentially controlled by malicious users. To address these challenges, we present AgenTEE, a system for deploying confidential agent pipelines on edge devices. AgenTEE places the agent runtime, inference engine, and third-party applications into independently attested confidential virtual machines (cVMs) and mediates their interaction through explicit, verifiable communication channels. Built on Arm Confidential Compute Architecture (CCA), a recent extension to Arm platforms, AgenTEE enforces strong system-level isolation of sensitive assets and runtime state. Our evaluation shows that such multi-cVMs system is practical, achieving near-native performance with less than 5.15% runtime overhead compared to commodity OS multi-process deployments.

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。

↑