PrivaSee AI: A Generative AI Framework for Dynamic Web Tracking Detection and Explainable Privacy Auditing
Modern websites use third-party scripts, cookies, and other tracking mechanisms that may collect information about users' browsing activities. Understanding these activities through conventional browser developer tools can be difficult for non-technical users. This paper presents PrivaSee AI, a prototype framework for dynamic web privacy auditing and explainable privacy analysis. The system uses Puppeteer and headless Chromium to observe website behaviour, collect cookies, enumerate scripts, and inspect selected HTTP security headers, including Content-Security-Policy, Strict-Transport-Security, and X-Frame-Options. The collected telemetry is processed using Google Gemini 2.5 Flash to generate structured privacy explanations, including a privacy grade, privacy story, creepiness report, and security assessment. The authors report an exploratory evaluation across 50 websites from five industry sectors and a usability study involving 15 university students. The reported results indicate an improvement in mean self-rated comprehension from 1.87 to 4.73 on a five-point scale. The findings are preliminary and require verification against the original experimental records. PrivaSee AI is intended to improve privacy awareness and explainability rather than provide a complete security or legal compliance assessment. Keywords: Explainable AI, Web Privacy, Dynamic Tracking Detection, Puppeteer, Chromium, Gemini, Browser Telemetry, Privacy Auditing.
Authors
- M.Geetha
- L. Jaya Sai Reddy
Institutions
- Rajiv Gandhi University of Knowledge Technologies (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-15
- DOI
- https://doi.org/10.5281/zenodo.24241127
- Primary Topic
- Privacy, Security, and Data Protection
- Type
- article
- Field-Weighted Citation Impact
- 0.00