评测智能网页代理的隐私泄露风险，发现主流模型常过度使用敏感信息。
AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
- 构建端到端基准AgentDAM，测试代理是否仅在必要时使用敏感信息。
- GPT-4、Llama-3、Claude等模型普遍存在非必要信息处理问题。
- 提出提示防御法降低泄露，适合关注AI隐私安全的研究者参考。
能够遵循指令并完成复杂多步任务的自主AI代理有望极大提升人类生产力。然而，为完成诸多任务，这些代理需访问用户个人数据，引发其是否能合理使用此类信息的担忧。本文提出新基准AgentDAM，用于评估AI网页导航代理是否遵循“数据最小化”隐私原则——即仅在必要时使用潜在敏感信息。该基准模拟真实网页交互场景，可适配所有现有网页导航代理。我们利用AgentDAM评估基于GPT-4、Llama-3和Claude构建的代理，发现它们普遍存在非必要敏感信息的无意使用。此外，我们提出一种基于提示的防御方法，有效减少信息泄露，并证明端到端基准比直接探查LLM隐私更真实。结果表明，亟需研究能在推理阶段优先考虑数据最小化的AI代理。
原文摘要 · Abstract (English)
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their users, raising the question of whether they are capable of using it appropriately. In this work, we introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of ``data minimization''. For the purposes of our benchmark, data minimization means that the agent uses a piece of potentially sensitive information only if it is ``necessary'' to complete a particular task. Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents. We use AgentDAM to evaluate how well AI agents built on top of GPT-4, Llama-3 and Claude can limit processing of potentially private information, and show that they are prone to inadvertent use of unnecessary sensitive information. We also propose a prompting-based defense that reduces information leakage, and demonstrate that our end-to-end benchmarking provides a more realistic measure than probing LLMs about privacy. Our results highlight that further research is needed to develop AI agents that can prioritize data minimization at inference time.
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。