PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents

要旨

While web agents gained popularity by automating web interactions, their requirement for interface access introduces privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found that users frequently misunderstand agent data practices, and desire unobtrusive, transparent data management. To achieve this, we developed PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces based on user preferences. It employs a tiered delegation to balance automation and intrusiveness, using ambient notifications for low-sensitivity data and enforces a mandatory pause for high-sensitivity data. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks showed that PrivWeb enhances perceived privacy protection and trust compared to transparency-only baselines, without increasing cognitive load. Crucially, we identified user delegation strategies: they prefer to manually execute sensitive steps for high-sensitivity data, while granting agent access to low-sensitivity data.

著者
Shuning Zhang
Tsinghua University, Beijing, China
Yutong Jiang
Tongji University, Shanghai, China
Rongjun Ma
Aalto University , Espoo, Finland
Yuting Yang
University of Michigan, Ann Arbor, Michigan, United States
Mingyao Xu
University of Washington, Seattle, Washington, United States
Zhixin Huang
Shantou University, Shantou, China
Xin Yi
Tsinghua University, Beijing, China
Hewu Li
Tsinghua University, Beijing, China

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI Governance and Accountability

Area 1 + 2 + 3: theatre
7 件の発表
2026-04-13 20:15:00
2026-04-13 21:45:00