Automated Privacy Information Annotation in Large Language Model Interactions

• URL: http://arxiv.org/abs/2505.20910v1
• Date: Tue, 27 May 2025 09:00:12 GMT
• Title: Automated Privacy Information Annotation in Large Language Model Interactions
• Authors: Hang Zeng, Xiangyu Liu, Yong Hu, Chaoyue Niu, Fan Wu, Shaojie Tang, Guihai Chen,
• Abstract summary: Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information.<n>Existing privacy detection methods were designed for different objectives and application scenarios.<n>We construct a large-scale multilingual dataset with 249K user queries and 154K annotated privacy phrases.
• Score: 40.87806981624453
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private information has therefore become a practical need. Existing privacy detection methods, however, were designed for different objectives and application scenarios, typically tagging personally identifiable information (PII) in anonymous content. In this work, to support the development and evaluation of privacy detection models for LLM interactions that are deployable on local user devices, we construct a large-scale multilingual dataset with 249K user queries and 154K annotated privacy phrases. In particular, we build an automated privacy annotation pipeline with cloud-based strong LLMs to automatically extract privacy phrases from dialogue datasets and annotate leaked information. We also design evaluation metrics at the levels of privacy leakage, extracted privacy phrase, and privacy information. We further establish baseline methods using light-weight LLMs with both tuning-free and tuning-based methods, and report a comprehensive evaluation of their performance. Evaluation results reveal a gap between current performance and the requirements of real-world LLM applications, motivating future research into more effective local privacy detection methods grounded in our dataset.

Related papers

• Controlling What You Share: Assessing Language Model Adherence to Privacy Preferences [80.63946798650653]
  We explore how users can stay in control of their data by using privacy profiles.<n>We build a framework where a local model uses these instructions to rewrite queries.<n>To support this research, we introduce a multilingual dataset of real user queries to mark private content.
  arXiv  Detail & Related papers  (2025-07-07T18:22:55Z)
• MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation [54.410825977390274]
  Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks.<n>We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains.<n>We then evaluate the current state-of-the-art LLMs on their understanding of contextually private data and their ability to collaborate without violating user privacy.
  arXiv  Detail & Related papers  (2025-06-25T18:04:25Z)
• PRIV-QA: Privacy-Preserving Question Answering for Cloud Large Language Models [10.050972891318324]
  We propose a privacy preservation pipeline for protecting privacy and sensitive information during interactions between users and large language models.<n>We construct SensitiveQA, the first privacy open-ended question-answering dataset.<n>Our proposed solution employs a multi-stage strategy aimed at preemptively securing user information while simultaneously preserving the response quality of cloud-based LLMs.
  arXiv  Detail & Related papers  (2025-02-19T09:17:07Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories.<n>We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds.<n>State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• On Protecting the Data Privacy of Large Language Models (LLMs): A Survey [35.48984524483533]
  Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. LLMs process and generate large amounts of data, which may threaten data privacy.
  arXiv  Detail & Related papers  (2024-03-08T08:47:48Z)
• Privacy Preserving Large Language Models: ChatGPT Case Study Based Vision and Framework [6.828884629694705]
  This article proposes the conceptual model called PrivChatGPT, a privacy-generative model for LLMs. PrivChatGPT consists of two main components i.e., preserving user privacy during the data curation/pre-processing together with preserving private context and the private training process for large-scale data.
  arXiv  Detail & Related papers  (2023-10-19T06:55:13Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.