arXiv cs.CY· Paschalis Bekos, Billy Tsouvalas, Nick Nikiforakis, Michalis Polychronakis·· 11 小时前AI 评分58
研究测量 42 个 AI 聊天平台的上下文泄露：21 个泄露对话标题，9 个泄露原始提示词
Penny for Your Prompts: A Measurement Study of Contextual Leakage in AI Chat Platforms
AI 导读
研究对 42 个通用及垂直领域（健康、法律、教育）AI 聊天平台的网页界面做了大规模测量，发现 21 个平台把对话标题泄露给第三方追踪器，9 个平台泄露了用户原始提示词。研究还在 JavaScript 引擎层把每条数据流归因到触发它的具体用户操作和 DOM 抓取机制，并观察到大量平台将用户邮箱发送给第三方追踪器，使对话上下文可与用户身份关联。该论文将发表于 IEEE S&P，2027 年 5 月。
正文 · 原文
Abstract:AI chatbot platforms have become one of the most popular web interfaces users interact with online, routinely receiving personal and intimate information shared under an expectation of privacy. Yet, on the web application side, these platforms have the ability to embed third-party analytics, advertising, and session replay scripts that operate silently alongside the chatbot, creating an underexamined channel for conversational data leakage towards third parties. We conduct the first systematic large-scale measurement study of contextual leakage in AI chatbots, auditing the web interfaces of 42 general-purpose and domain-specific (health, legal, and education) platforms. Beyond standard network interception, we instrument the browser at the JavaScript engine level to attribute each data flow to the exact user action that triggered it, and the DOM capture mechanism used to retrieve its content, a granularity invisible to network-layer analysis alone. We find that 21 of these platforms leak conversation titles to third-party trackers, while nine leak verbatim user prompts. Beyond content, we observe a substantial amount of chatbot platforms sending user emails to third-party trackers, enabling the association of conversational context with a user's identity. Our findings cast traditional web privacy issues under a new light, highlighting the privacy issues that are inherent in how users interact with modern AI chatbots.
| Comments: | To appear in the IEEE Symposium on Security & Privacy (S&P), May 2027 |
| Subjects: | Cryptography and Security (cs.CR); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.37467 [cs.CR] |
| (or arXiv:2610.37467v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37467 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Paschalis Bekos [view email]
[v1]
Tue, 27 Oct 2026 16:01:08 UTC (3,020 KB)
来源：arXiv cs.CY · arxiv.org