# AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

arXiv: https://arxiv.org/abs/2409.17642 · HTML: https://mlsanity.com/paper/2409.17642/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 71 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [UFO: A UI-Focused Agent for Windows OS Interaction](https://mlsanity.com/paper/2402.07939/) (2024)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation](https://mlsanity.com/paper/2309.11765/) (2023)
- [Conversational Health Agents: A Personalized LLM-Powered Agent Framework](https://mlsanity.com/paper/2310.02374/) (2023)
- [TaskWeaver: A Code-First Agent Framework](https://mlsanity.com/paper/2311.17541/) (2023)
- [DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer](https://mlsanity.com/paper/2312.03724/) (2023)
- [Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild](https://mlsanity.com/paper/2407.11438/) (2024)
- [Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services](https://mlsanity.com/paper/2305.06212/) (2023)
- [Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering](https://mlsanity.com/paper/2305.11541/) (2023)
- [Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate](https://mlsanity.com/paper/2401.16788/) (2024)
- [Privately Fine-Tuning Large Language Models with Differential Privacy](https://mlsanity.com/paper/2210.15042/) (2022)
- [Operationalizing Contextual Integrity in Privacy-Conscious Assistants](https://mlsanity.com/paper/2408.02373/) (2024)
- [How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities](https://mlsanity.com/paper/2311.09447/) (2023)
- [An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors](https://mlsanity.com/paper/2309.14510/) (2023)
- [A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures](https://mlsanity.com/paper/2303.00164/) (2023)
- [The Vision of Autonomic Computing: Can LLMs Make It a Reality?](https://mlsanity.com/paper/2407.14402/) (2024)

## Built on by (most cited first, 2 of 2)

- [Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent](https://mlsanity.com/paper/2411.01344/) (2024)
- [IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces](https://mlsanity.com/paper/2504.21347/) (2025)

## Abstract (arXiv)

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.