AudAgent: AI代理隐私政策合规性自动审计
AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
AI总结：
AudAgent通过自动化隐私审计工具，实时监控AI代理的数据实践，确保其符合声明的隐私政策，并可视化检测到的隐私违规行为。
摘要：
AI代理可以自主执行任务，并且常常在没有明确用户同意的情况下收集或披露用户的敏感本地数据，这引发了严重的隐私问题。尽管AI代理的隐私政策描述了其预期的数据实践，但仍然缺乏关于运行时行为是否符合这些政策的透明度和问责制。为弥合这一差距，我们提出了AudAgent，一个持续监控AI代理数据实践并确保符合其声明隐私政策的工具。AudAgent包含四个组件用于自动化AI代理的隐私审计。（i）政策形式化：一种新颖的跨LLM投票机制，确保将隐私政策高信心地解析为形式模型。（ii）运行时注释：一种轻量级的Presidio基础分析器，通过AI代理的上下文和形式化的隐私政策模型检测敏感数据并注释数据实践。（iii）合规审计：本体图和自动机基于检查，将隐私政策模型与运行时注释联系起来，实现即席合规验证。（iv）用户界面：一种不依赖基础设施的实现，可视化AI代理的实时执行轨迹以及检测到的隐私违规，提供用户友好的透明度和问责制。我们对使用主流框架构建的AI代理评估AudAgent，证明其在检测和可视化隐私政策违规方面的有效性。使用AudAgent，我们进一步发现许多隐私政策缺乏对高度敏感数据如SSN的明确保护措施，其滥用违反法律要求，且许多代理，包括由Claude、Gemini和DeepSeek驱动的代理，不拒绝通过第三方工具处理此类数据。AudAgent主动阻止对这些数据的操作，覆盖代理的原始隐私政策和行为。
英文摘要：
AI agents can autonomously perform tasks and, often without explicit user consent, collect or disclose users' sensitive local data, which raises serious privacy concerns. Although AI agents' privacy policies describe their intended data practices, there remains limited transparency and accountability about whether runtime behavior matches those policies. To bridge this gap, we present AudAgent, a tool that continuously monitors AI agents' data practices in real time and guards compliance with their stated privacy policies. AudAgent comprises four components for automated privacy auditing of AI agents. (i) Policy formalization: a novel cross-LLM voting mechanism that ensures high-confidence parsing of privacy policies into formal models. (ii) Runtime annotation: a lightweight Presidio-based analyzer that detects sensitive data and annotates data practices based on the AI agent's context and the formalized privacy policy model. (iii) Compliance auditing: ontology graphs and automata-based checking that link the privacy policy model with runtime annotations, enabling on-the-fly compliance verification. (iv) User interface: an infrastructure-independent implementation that visualizes the real-time execution trace of AI agents alongside detected privacy violations, providing user-friendly transparency and accountability. We evaluate AudAgent on AI agents built with mainstream frameworks, demonstrating its effectiveness in detecting and visualizing privacy policy violations. Using AudAgent, we further find that many privacy policies lack explicit safeguards for highly sensitive data such as SSNs, whose misuse violates legal requirements, and that many agents, including those powered by Claude, Gemini, and DeepSeek,do not refuse to process such data via third-party tools. AudAgent proactively blocks operations on such data, overriding the agents' original privacy policies and behavior.
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。
