mlsanityData to 14 Oct 2026

DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts

arXiv 2609.29684 ↗First posted 31 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite the strengths of modern anonymization and de-identification techniques, the risk of re-identification remains significant due to the indirect identifiers remaining in texts. To address this problem, recent works have applied text rewriting under Differential Privacy (DP) to prevent data linkage by perturbing texts via noise addition. Such methods privatize all tokens in a text indiscriminately, diminishing text quality and usability in critical domains such as in clinical settings. Focusing on indirect personal identifiers (IPIs), we introduce a utility-preserving DP text rewriting method that only privatizes spans containing IPIs. We show that our method effectively reduces re-identification risks in clinical texts while being producing more coherent and usable output texts, leading to higher privacy-utility trade-offs. In this, we demonstrate the effectiveness of hybrid text privatization, which leverages the promise of DP in an efficient, usable manner.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

25 of 44 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  7. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 195
  8. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  9. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 119
  10. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
  11. 2022The Limits of Word Level Differential Privacycited by 63
  12. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
13 more
  1. 2021Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integrationcited by 44
  2. 2019ER-AE: Differentially Private Text Generation for Authorship Anonymizationcited by 35
  3. 2019SoK: Differential Privaciescited by 34
  4. 2022DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewritingcited by 28
  5. 2024DP-MLM: Differentially Private Text Rewriting Using Masked Language Modelscited by 24
  6. 2024A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-offcited by 13
  7. 2024On the Vulnerability of Text Sanitizationcited by 9
  8. 2025On the Impact of Noise in Differentially Private Text Rewritingcited by 8
  9. 2025Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewritingcited by 5
  10. 2023To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?cited by 3
  11. 2026MultiGraSCCo: A Multilingual Anonymization Benchmark with Annotations of Personal Identifierscited by 3
  12. 2025Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Textscited by 2
  13. 2025Inspecting the Representation Manifold of Differentially-Private Textcited by 2

Built on by

Not cited yet.