Stronger Re-identification Attacks through Reasoning and Aggregation

• URL: http://arxiv.org/abs/2510.09184v1
• Date: Fri, 10 Oct 2025 09:27:42 GMT
• Title: Stronger Re-identification Attacks through Reasoning and Aggregation
• Abstract summary: This paper presents two complementary strategies to build stronger re-identification attacks.<n>We first show that the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results.<n>We also find that reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.
• Score: 8.823317238417832
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has shown how the robustness of de-identification methods could be assessed by attempting the reverse process of _re-identification_, based on an automated adversary using its background knowledge to uncover the PIIs that have been masked. This paper presents two complementary strategies to build stronger re-identification attacks. We first show that (1) the _order_ in which the PII spans are re-identified matters, and that aggregating predictions across multiple orderings leads to improved results. We also find that (2) reasoning models can boost the re-identification performance, especially when the adversary is assumed to have access to extensive background knowledge.

Related papers

• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• WithAnyone: Towards Controllable and ID Consistent Image Generation [83.55786496542062]
  Identity-consistent generation has become an important focus in text-to-image research.<n>We develop a large-scale paired dataset tailored for multi-person scenarios.<n>We propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity.
  arXiv  Detail & Related papers  (2025-10-16T17:59:54Z)
• Emergent AI Surveillance: Overlearned Person Re-Identification and Its Mitigation in Law Enforcement Context [2.3124669700253553]
  Generic instance search models can dramatically reduce the manual effort required to analyze vast surveillance footage during criminal investigations by retrieving specific objects of interest to law enforcement.<n>However, our research reveals an unintended emergent capability: through overlearning, these models can single out specific individuals even when trained on datasets without human subjects.<n>This capability raises concerns regarding identification and profiling of individuals based on their personal data.
  arXiv  Detail & Related papers  (2025-10-07T15:23:16Z)
• Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2) [13.726589034127025]
  We propose and discuss a patch-based methodology to preserve privacy in fake ID detection research.<n>We provide a new public database, FakeIDet2-db, comprising over 900K real/fake ID patches extracted from 2,000 ID images.<n>We present a new privacy-aware fake ID detection method, FakeIDet2.
  arXiv  Detail & Related papers  (2025-08-14T17:30:36Z)
• Re-identification of De-identified Documents with Autoregressive Infilling [2.2406151150434894]
  We present a novel, RAG-inspired approach that attempts the reverse process of re-identification based on a database of documents representing background knowledge.<n>As many as 80% of de-identified text spans can be successfully recovered and the re-identification accuracy increases along with the level of background knowledge.
  arXiv  Detail & Related papers  (2025-05-19T08:43:54Z)
• iFADIT: Invertible Face Anonymization via Disentangled Identity Transform [51.123936665445356]
  Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy.<n>This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform.
  arXiv  Detail & Related papers  (2025-01-08T10:08:09Z)
• ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning [57.91881829308395]
  Identity-preserving text-to-image generation (ID-T2I) has received significant attention due to its wide range of application scenarios like AI portrait and advertising. We present textbfID-Aligner, a general feedback learning framework to enhance ID-T2I performance.
  arXiv  Detail & Related papers  (2024-04-23T18:41:56Z)
• Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification [55.741525129613535]
  "Disentangle Before Anonymize" is a novel two-stage Framework(DBAF)<n>This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module.<n>Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches.
  arXiv  Detail & Related papers  (2023-11-15T08:59:02Z)
• Diff-Privacy: Diffusion-based Face Privacy Protection [58.1021066224765]
  In this paper, we propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy. Specifically, we train our proposed multi-scale image inversion module (MSI) to obtain a set of SDM format conditional embeddings of the original image. Based on the conditional embeddings, we design corresponding embedding scheduling strategies and construct different energy functions during the denoising process to achieve anonymization and visual identity information hiding.
  arXiv  Detail & Related papers  (2023-09-11T09:26:07Z)
• Unsupervised Text Deidentification [101.2219634341714]
  We propose an unsupervised deidentification method that masks words that leak personally-identifying information. Motivated by K-anonymity based privacy, we generate redactions that ensure a minimum reidentification rank.
  arXiv  Detail & Related papers  (2022-10-20T18:54:39Z)

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.