CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Chaoran, Zhou, Daodao, Ye, Yanfang, Li, Toby Jia-jun, Yao, Yaxing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910797025771520
author Chen, Chaoran
Zhou, Daodao
Ye, Yanfang
Li, Toby Jia-jun
Yao, Yaxing
author_facet Chen, Chaoran
Zhou, Daodao
Ye, Yanfang
Li, Toby Jia-jun
Yao, Yaxing
contents The rise of end-user applications powered by large language models (LLMs), including both conversational interfaces and add-ons to existing graphical user interfaces (GUIs), introduces new privacy challenges. However, many users remain unaware of the risks. This paper explores methods to increase user awareness of privacy risks associated with LLMs in end-user applications. We conducted five co-design workshops to uncover user privacy concerns and their demand for contextual privacy information within LLMs. Based on these insights, we developed CLEAR (Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation), a just-in-time contextual assistant designed to help users identify sensitive information, summarize relevant privacy policies, and highlight potential risks when sharing information with LLMs. We evaluated the usability and usefulness of CLEAR across two example domains: ChatGPT and the Gemini plugin in Gmail. Our findings demonstrated that CLEAR is easy to use and improves users' understanding of data practices and privacy risks. We also discussed LLM's duality in posing and mitigating privacy risks, offering design and policy implications.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications
Chen, Chaoran
Zhou, Daodao
Ye, Yanfang
Li, Toby Jia-jun
Yao, Yaxing
Human-Computer Interaction
The rise of end-user applications powered by large language models (LLMs), including both conversational interfaces and add-ons to existing graphical user interfaces (GUIs), introduces new privacy challenges. However, many users remain unaware of the risks. This paper explores methods to increase user awareness of privacy risks associated with LLMs in end-user applications. We conducted five co-design workshops to uncover user privacy concerns and their demand for contextual privacy information within LLMs. Based on these insights, we developed CLEAR (Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation), a just-in-time contextual assistant designed to help users identify sensitive information, summarize relevant privacy policies, and highlight potential risks when sharing information with LLMs. We evaluated the usability and usefulness of CLEAR across two example domains: ChatGPT and the Gemini plugin in Gmail. Our findings demonstrated that CLEAR is easy to use and improves users' understanding of data practices and privacy risks. We also discussed LLM's duality in posing and mitigating privacy risks, offering design and policy implications.
title CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications
topic Human-Computer Interaction
url https://arxiv.org/abs/2410.13387