You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence

• URL: http://arxiv.org/abs/2601.04265v1
• Date: Wed, 07 Jan 2026 07:54:23 GMT
• Title: You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence
• Authors: Weihao Shen, Yaxin Xu, Shuang Li, Wei Chen, Yuqin Lan, Meng Yuan, Fuzhen Zhuang,
• Abstract summary: We propose a utility-preserving anonymization approach that performs intent-conditioned exposure control.<n>IntentAnony models pragmatic intent and constructs privacy inference evidence chains.<n>Results show an approximately 30% improvement in the overall privacy--utility trade-off.
• Score: 25.1631668864743
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative intent and obscure necessary information. This is particularly problematic when personal attributes are integral to expressive or pragmatic goals. The central challenge lies in determining which attributes to protect, and to what extent, while preserving semantic and pragmatic functions. We propose IntentAnony, a utility-preserving anonymization approach that performs intent-conditioned exposure control. IntentAnony models pragmatic intent and constructs privacy inference evidence chains to capture how distributed cues support attribute inference. Conditioned on intent, it assigns each attribute an exposure budget and selectively suppresses non-intent inference pathways while preserving intent-relevant content, semantic structure, affective nuance, and interactional function. We evaluate IntentAnony using privacy inference success rates, text utility metrics, and human evaluation. The results show an approximately 30% improvement in the overall privacy--utility trade-off, with notably stronger usability of anonymized text compared to prior state-of-the-art methods. Our code is available at https://github.com/Nevaeh7/IntentAnony.

Related papers

• Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs [61.15237978606501]
  Large language models can infer private user attributes from user-generated text.<n>Existing anonymization-based defenses are coarse-grained, lacking word-level precision in anonymizing privacy-leaking elements.<n>We propose a unified defense framework that combines fine-grained anonymization (TRACE) with inference-preventing optimization (RPS)
  arXiv  Detail & Related papers  (2026-02-12T03:37:50Z)
• Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search [60.197239728279534]
  Large language models (LLMs) in cloud-based services have raised significant privacy concerns.<n>Existing text anonymization and de-identification techniques, such as rule-based redaction and scrubbing, often struggle to balance privacy preservation with text naturalness and utility.<n>We propose a zero-shot, tree-search-based iterative sentence rewriting algorithm that systematically obfuscates or deletes private information while preserving coherence, relevance, and naturalness.
  arXiv  Detail & Related papers  (2025-09-25T07:23:52Z)
• VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks [51.68795949691009]
  We introduce VoxGuard, a framework grounded in differential privacy and membership inference.<n>For attributes, we show that simple transparent attacks recover gender and accent with near-perfect accuracy even after anonymization.<n>Our results demonstrate that EER substantially underestimates leakage, highlighting the need for low-FPR evaluation.
  arXiv  Detail & Related papers  (2025-09-22T20:57:48Z)
• 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.<n>By incorporating both semantic and contextual nuances, dchi-stencil achieves a robust balance between privacy and utility.<n>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)
• Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy [64.32494202656801]
  Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence.<n>We present anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context.<n>We also proposeMaskDP to protect non-anonymized but privacy sensitive background information.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• IDT: Dual-Task Adversarial Attacks for Privacy Protection [8.312362092693377]
  Methods to protect privacy can involve using representations inside models that are not to detect sensitive attributes. We propose IDT, a method that analyses predictions made by auxiliary and interpretable models to identify which tokens are important to change. We evaluate different datasets for NLP suitable for different tasks.
  arXiv  Detail & Related papers  (2024-06-28T04:14:35Z)
• Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition [18.93148005536135]
  Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of interpretability. We propose a solution: Human selected privacy templates that yield interpretability by design, an obfuscation scheme that selectively hides attributes and also induces temporal consistency.
  arXiv  Detail & Related papers  (2024-03-19T13:17:26Z)
• GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions [43.017036538109274]
  GANonymization is a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN)
  arXiv  Detail & Related papers  (2023-05-03T14:22:48Z)
• Human intuition as a defense against attribute inference [4.916067949075847]
  Attribute inference has become a major threat to privacy. One way to tackle this threat is to strategically modify one's publicly available data in order to keep one's private information hidden from attribute inference. We evaluate people's ability to perform this task, and compare it against algorithms designed for this purpose.
  arXiv  Detail & Related papers  (2023-04-24T06:54:17Z)
• SPAct: Self-supervised Privacy Preservation for Action Recognition [73.79886509500409]
  Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. We present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels.
  arXiv  Detail & Related papers  (2022-03-29T02:56:40Z)
• 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)
• Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text [2.9005223064604078]
  We develop a new approach to authorship anonymization by constructing a generative adversarial network. Our fully automatic method achieves comparable results to other methods in terms of content preservation and fluency. Our approach is able to generalize well to an open-set context and anonymize sentences from authors it has not encountered before.
  arXiv  Detail & Related papers  (2021-10-18T17:45:56Z)
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation [77.49428268918703]
  We study techniques that allow individuals to limit the private information leaked in visual data. We tackle this problem in a novel image obfuscation framework. We find our approach generates obfuscated images faithful to the original input images, and additionally increase uncertainty by 6.2$times$ (or up to 0.85 bits) over the non-obfuscated counterparts.
  arXiv  Detail & Related papers  (2020-05-20T19:48:04Z)

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.