为语言模型控制电脑设计安全访问框架，防误操作且性能损失极小。
Secure and Efficient Access Control for Computer-Use Agents via Context Space
- 基于上下文与用户意图的静态策略，动态约束代理行为。
- 在基准测试中100%防御攻击，性能损耗仅1.99%。
- 支持多种交互接口，适合开发安全可控的AI助手。
基于大语言模型（LLM）的计算机使用代理融合了人工智能与操作系统能力，可通过自然语言控制系统及应用级功能。然而，由于LLM固有的不确定性，赋予代理对计算机的控制权带来重大安全风险；当代理行为偏离用户意图时，可能造成不可逆后果。现有缓解方法如用户确认和基于LLM的动态动作验证，在可用性、安全性与性能方面仍存在局限。为此，我们提出CSAgent——一种面向计算机使用代理的系统级静态策略访问控制框架。为弥合静态策略与动态上下文及用户意图之间的差距，CSAgent引入意图与上下文感知策略，并提供自动化工具链协助开发者构建与优化策略。该框架通过优化的OS服务执行策略，确保代理行为仅在特定用户意图与上下文中允许执行。CSAgent支持通过API、CLI和GUI等多种接口保护计算机控制代理。我们实现了该系统并进行了评估，结果表明其在基准测试中成功防御所有攻击，同时仅引入1.99%的性能开销和5.42%的可用性下降。
原文摘要 · Abstract (English)
Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues, granting agents control over computers poses significant security risks. When agent actions deviate from user intentions, they can cause irreversible consequences. Existing mitigation approaches, such as user confirmation and LLM-based dynamic action validation, still suffer from limitations in usability, security, and performance. To address these challenges, we propose CSAgent, a system-level, static policy-based access control framework for computer-use agents. To bridge the gap between static policy and dynamic context and user intent, CSAgent introduces intent- and context-aware policies, and provides an automated toolchain to assist developers in constructing and refining them. CSAgent enforces these policies through an optimized OS service, ensuring that agent actions can only be executed under specific user intents and contexts. CSAgent supports protecting agents that control computers through diverse interfaces, including API, CLI, and GUI. We implement and evaluate CSAgent, which successfully defends against all attacks in the benchmarks while introducing only 1.99% performance overhead and 5.42% utility decrease.
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。