Stronger Re-identification Attacks through Reasoning and Aggregation
Preprint
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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Re-identification of De-identified Documents with Autoregressive Infilling2025
- Evaluating the disclosure risk of anonymized documents via a machine learning-based re-identification attackData Mining and Knowledge Discovery, 2024
- De-identification of clinical free text using natural language processing: A systematic review of current approachesArtificial Intelligence in Medicine, 2024
- In-Context Retrieval-Augmented Language ModelsTransactions of the Association for Computational Linguistics, 2023
- The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text AnonymizationComputational Linguistics, 2022
- Unsupervised Text Deidentification2022
- De-identification of patient notes with recurrent neural networksJournal of the American Medical Informatics Association, 2016
- C‐sanitized: A privacy model for document redaction and sanitizationJournal of the Association for Information Science and Technology, 2015
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009
- Automated de-identification of free-text medical recordsBMC Medical Informatics and Decision Making, 2008