AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
This addresses privacy risks in AI delegates for users in social interactions, though it appears incremental by building on existing privacy-focused research.
The paper tackles the challenge of balancing privacy protection with the need for strategic self-disclosure in AI delegates used for social tasks, proposing a novel system that enables privacy-conscious self-disclosure based on user perceptions from a pilot study.
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.