Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17642 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913937246650368 |
|---|---|
| author | Zhang, Zhiyang Chen, Xi Yang, Fangkai Qin, Xiaoting Du, Chao Cheng, Xi Liu, Hangxin Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei |
| author_facet | Zhang, Zhiyang Chen, Xi Yang, Fangkai Qin, Xiaoting Du, Chao Cheng, Xi Liu, Hangxin Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei |
| contents | Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces. Despite their advantages, concerns arise regarding the potential risk of privacy leaks, particularly in scenarios involving social interactions. While existing research has focused on protecting privacy by limiting the access of AI delegates to sensitive user information, many social scenarios require disclosing private details to achieve desired social goals, necessitating a balance between privacy protection and disclosure. To address this challenge, we first conduct a pilot study to investigate user perceptions of AI delegates across various social relations and task scenarios, and then propose a novel AI delegate system that enables privacy-conscious self-disclosure. Our user study demonstrates that the proposed AI delegate strategically protects privacy, pioneering its use in diverse and dynamic social interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17642 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure Zhang, Zhiyang Chen, Xi Yang, Fangkai Qin, Xiaoting Du, Chao Cheng, Xi Liu, Hangxin Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Artificial Intelligence Computers and Society Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces. Despite their advantages, concerns arise regarding the potential risk of privacy leaks, particularly in scenarios involving social interactions. While existing research has focused on protecting privacy by limiting the access of AI delegates to sensitive user information, many social scenarios require disclosing private details to achieve desired social goals, necessitating a balance between privacy protection and disclosure. To address this challenge, we first conduct a pilot study to investigate user perceptions of AI delegates across various social relations and task scenarios, and then propose a novel AI delegate system that enables privacy-conscious self-disclosure. Our user study demonstrates that the proposed AI delegate strategically protects privacy, pioneering its use in diverse and dynamic social interactions. |
| title | AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2409.17642 |