PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918141225861120 |
|---|---|
| author | Zhang, Shuning Jiang, Yutong Ma, Rongjun Yang, Yuting Xu, Mingyao Huang, Zhixin Yi, Xin Li, Hewu |
| author_facet | Zhang, Shuning Jiang, Yutong Ma, Rongjun Yang, Yuting Xu, Mingyao Huang, Zhixin Yi, Xin Li, Hewu |
| contents | While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found users frequently misunderstand agents' data practices, and desired unobtrusive, transparent data management. To achieve this, we designed and implemented PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces according to user preferences. It features privacy categorization schema and adaptive notifications that selectively pauses tasks for user control over information collection for highly sensitive information, while offering non-disruptive options for less sensitive information, minimizing human oversight. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks compared PrivWeb with baselines without notification and without control for private information access, where PrivWeb reduced perceived privacy risks with no associated increase in cognitive effort, and resulted in higher overall satisfaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11939 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents Zhang, Shuning Jiang, Yutong Ma, Rongjun Yang, Yuting Xu, Mingyao Huang, Zhixin Yi, Xin Li, Hewu Human-Computer Interaction While web agents gained popularity by automating web interactions, their requirement for interface access introduces significant privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found users frequently misunderstand agents' data practices, and desired unobtrusive, transparent data management. To achieve this, we designed and implemented PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces according to user preferences. It features privacy categorization schema and adaptive notifications that selectively pauses tasks for user control over information collection for highly sensitive information, while offering non-disruptive options for less sensitive information, minimizing human oversight. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks compared PrivWeb with baselines without notification and without control for private information access, where PrivWeb reduced perceived privacy risks with no associated increase in cognitive effort, and resulted in higher overall satisfaction. |
| title | PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web Agents |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.11939 |