NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human

• URL: http://arxiv.org/abs/2406.03749v2
• Date: Tue, 27 May 2025 00:59:38 GMT
• Title: NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
• Authors: Shuo Huang, William MacLean, Xiaoxi Kang, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari, Lizhen Qu,
• Abstract summary: We suggest sanitizing sensitive text using two common strategies used by humans.<n>We curate the first corpus, coined NAP2, through both crowdsourcing and the use of large language models.<n>Compared to the prior works on anonymization, the human-inspired approaches result in more natural rewrites.
• Score: 56.46355425175232
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The widespread use of cloud-based Large Language Models (LLMs) has heightened concerns over user privacy, as sensitive information may be inadvertently exposed during interactions with these services. To protect privacy before sending sensitive data to those models, we suggest sanitizing sensitive text using two common strategies used by humans: i) deleting sensitive expressions, and ii) obscuring sensitive details by abstracting them. To explore the issues and develop a tool for text rewriting, we curate the first corpus, coined NAP^2, through both crowdsourcing and the use of large language models (LLMs). Compared to the prior works on anonymization, the human-inspired approaches result in more natural rewrites and offer an improved balance between privacy protection and data utility, as demonstrated by our extensive experiments. Researchers interested in accessing the dataset are encouraged to contact the first or corresponding author via email.

Related papers

• T2UE: Generating Unlearnable Examples from Text Descriptions [60.111026156038264]
  Unlearnable Examples (UEs) have emerged as a promising countermeasure against unauthorized model training.<n>We introduce textbfText-to-Unlearnable Example (T2UE), a novel framework that enables users to generate UEs using only text descriptions.
  arXiv  Detail & Related papers  (2025-08-05T05:10:14Z)
• A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage [77.83757117924995]
  We propose a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release. Our approach shows that seemingly innocuous auxiliary information can be used to infer sensitive attributes like age or substance use history from sanitized data.
  arXiv  Detail & Related papers  (2025-04-28T01:16:27Z)
• Investigating User Perspectives on Differentially Private Text Privatization [81.59631769859004]
  This work investigates how factors of $textitscenario$, $textitdata sensitivity$, $textitmechanism type$, and $textitreason for data collection$ impact user preferences for text privatization. We learn that while all these factors play a role in influencing privacy decisions, users are highly sensitive to the utility and coherence of the private output texts.
  arXiv  Detail & Related papers  (2025-03-12T12:33:20Z)
• Token-Level Privacy in Large Language Models [7.4143291213663955]
  We introduce dchi-stencil, a novel token-level privacy-preserving mechanism that integrates contextual and semantic information. By incorporating both semantic and contextual nuances, dchi-stencil achieves a robust balance between privacy and utility. This work highlights the potential of dchi-stencil to set a new standard for privacy-preserving NLP in modern, high-risk applications.
  arXiv  Detail & Related papers  (2025-03-05T16:27:25Z)
• Truthful Text Sanitization Guided by Inference Attacks [2.824895388993495]
  The purpose of text sanitization is to rewrite those text spans in a document that may directly or indirectly identify an individual. We present an automated text sanitization strategy based on generalizations that subsume the semantic content of the original text spans.
  arXiv  Detail & Related papers  (2024-12-17T14:07:01Z)
• 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. 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.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild [40.57348900292574]
  Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy. We run an extensive, fine-grained analysis on the personal disclosures made by real users to commercial GPT models.
  arXiv  Detail & Related papers  (2024-07-16T07:05:31Z)
• 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)
• FLTrojan: Privacy Leakage Attacks against Federated Language Models Through Selective Weight Tampering [2.2194815687410627]
  We show how a malicious client can leak the privacy-sensitive data of some other users in FL even without any cooperation from the server.<n>Our best-performing method improves the membership inference recall by 29% and achieves up to 71% private data reconstruction.
  arXiv  Detail & Related papers  (2023-10-24T19:50:01Z)
• 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)
• ChatGPT for Us: Preserving Data Privacy in ChatGPT via Dialogue Text Ambiguation to Expand Mental Health Care Delivery [52.73936514734762]
  ChatGPT has gained popularity for its ability to generate human-like dialogue. Data-sensitive domains face challenges in using ChatGPT due to privacy and data-ownership concerns. We propose a text ambiguation framework that preserves user privacy.
  arXiv  Detail & Related papers  (2023-05-19T02:09:52Z)
• Planting and Mitigating Memorized Content in Predictive-Text Language Models [11.911353678499008]
  Language models are widely deployed to provide automatic text completion services in user products. Recent research has revealed that language models bear considerable risk of memorizing private training data. In this study, we test the efficacy of a range of privacy-preserving techniques to mitigate unintended memorization of sensitive user text.
  arXiv  Detail & Related papers  (2022-12-16T17:57:14Z)
• Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe [32.63295550058343]
  We show that a simple and practical recipe in the text domain is effective in generating useful synthetic text with strong privacy protection. Our method produces synthetic text that is competitive in terms of utility with its non-private counterpart.
  arXiv  Detail & Related papers  (2022-10-25T21:21:17Z)
• You Are What You Write: Preserving Privacy in the Era of Large Language Models [2.3431670397288005]
  We present an empirical investigation into the extent of the personal information encoded into pre-trained representations by a range of popular models. We show a positive correlation between the complexity of a model, the amount of data used in pre-training, and data leakage.
  arXiv  Detail & Related papers  (2022-04-20T11:12:53Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• Semantics-Preserved Distortion for Personal Privacy Protection in Information Management [65.08939490413037]
  This paper suggests a linguistically-grounded approach to distort texts while maintaining semantic integrity. We present two distinct frameworks for semantic-preserving distortion: a generative approach and a substitutive approach. We also explore privacy protection in a specific medical information management scenario, showing our method effectively limits sensitive data memorization.
  arXiv  Detail & Related papers  (2022-01-04T04:01:05Z)
• CAPE: Context-Aware Private Embeddings for Private Language Learning [0.5156484100374058]
  Context-Aware Private Embeddings (CAPE) is a novel approach which preserves privacy during training of embeddings. CAPE applies calibrated noise through differential privacy, preserving the encoded semantic links while obscuring sensitive information. Experimental results demonstrate that the proposed approach reduces private information leakage better than either single intervention.
  arXiv  Detail & Related papers  (2021-08-27T14:50:12Z)
• Privacy-Adaptive BERT for Natural Language Understanding [20.821155542969947]
  We study how to improve the effectiveness of NLU models under a Local Privacy setting using BERT. We propose privacy-adaptive LM pretraining methods and demonstrate that they can significantly improve model performance on privatized text input.
  arXiv  Detail & Related papers  (2021-04-15T15:01:28Z)

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.