PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

• URL: http://arxiv.org/abs/2409.00138v2
• Date: Thu, 17 Oct 2024 04:43:40 GMT
• Title: PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
• Authors: Yijia Shao, Tianshi Li, Weiyan Shi, Yanchen Liu, Diyi Yang,
• Abstract summary: PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. 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.
• Score: 54.11479432110771
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy norms becomes increasingly critical. However, quantifying the privacy norm awareness of LMs and the emerging privacy risk in LM-mediated communication is challenging due to (1) the contextual and long-tailed nature of privacy-sensitive cases, and (2) the lack of evaluation approaches that capture realistic application scenarios. To address these challenges, we propose PrivacyLens, a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories, enabling multi-level evaluation of privacy leakage in LM agents' actions. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. Using this dataset, we reveal a discrepancy between LM performance in answering probing questions and their actual behavior when executing user instructions in an agent setup. 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. We also demonstrate the dynamic nature of PrivacyLens by extending each seed into multiple trajectories to red-team LM privacy leakage risk. Dataset and code are available at https://github.com/SALT-NLP/PrivacyLens.

Related papers

• Can Humans Oversee Agents to Prevent Privacy Leakage? A Study on Privacy Awareness, Preferences, and Trust in Language Model Agents [1.5020330976600738]
  Language model (LM) agents that act on users' behalf for personal tasks can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee the privacy implications of the LM agents.
  arXiv  Detail & Related papers  (2024-11-02T19:15:42Z)
• 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)
• GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory [44.297102658873726]
  Existing research studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined patterns. We introduce a novel framework, GoldCoin, designed to efficiently ground LLMs in privacy laws for judicial assessing privacy violations. Our framework leverages the theory of contextual integrity as a bridge, creating numerous synthetic scenarios grounded in relevant privacy statutes.
  arXiv  Detail & Related papers  (2024-06-17T02:27:32Z)
• PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models [42.20437015301152]
  We present PrivLM-Bench, a benchmark for evaluating the privacy leakage of language models (LMs) Instead of only reporting DP parameters, PrivLM-Bench sheds light on the neglected inference data privacy during actual usage. We conduct extensive experiments on three datasets of GLUE for mainstream LMs.
  arXiv  Detail & Related papers  (2023-11-07T14:55:52Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• 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)
• Privacy Implications of Retrieval-Based Language Models [26.87950501433784]
  We present the first study of privacy risks in retrieval-based LMs, particularly $k$NN-LMs. We find that $k$NN-LMs are more susceptible to leaking private information from their private datastore than parametric models.
  arXiv  Detail & Related papers  (2023-05-24T08:37:27Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)
• PGLP: Customizable and Rigorous Location Privacy through Policy Graph [68.3736286350014]
  We propose a new location privacy notion called PGLP, which provides a rich interface to release private locations with customizable and rigorous privacy guarantee. Specifically, we formalize a user's location privacy requirements using a textitlocation policy graph, which is expressive and customizable. Third, we design a private location trace release framework that pipelines the detection of location exposure, policy graph repair, and private trajectory release with customizable and rigorous location privacy.
  arXiv  Detail & Related papers  (2020-05-04T04:25:59Z)

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.