mlsanityData to 14 Oct 2026

DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting

arXiv 2208.10400 ↗First posted 22 Aug 2022cs.CL cs.CRcited by 28

Not on the map. Why?

Abstract (arXiv)

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their privacy-preserving claims, leading to problems of transparency and reproducibility. We introduce DP-Rewrite, an open-source framework for differentially private text rewriting which aims to solve these problems by being modular, extensible, and highly customizable. Our system incorporates a variety of downstream datasets, models, pre-training procedures, and evaluation metrics to provide a flexible way to lead and validate private text rewriting research. To demonstrate our software in practice, we provide a set of experiments as a case study on the ADePT DP text rewriting system, detecting a privacy leak in its pre-training approach. Our system is publicly available, and we hope that it will help the community to make DP text rewriting research more accessible and transparent.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 10 of its 19 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

10 of 19 references.

References · 10

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  4. 2022The Limits of Word Level Differential Privacycited by 63
  5. 2019ER-AE: Differentially Private Text Generation for Authorship Anonymizationcited by 35
  6. 2019SoK: Differential Privaciescited by 34
  7. 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
  8. 2021When differential privacy meets NLP: The devil is in the detailcited by 25
  9. 2021Privacy-Preserving Graph Convolutional Networks for Text Classificationcited by 19
  10. 2022How reparametrization trick broke differentially-private text representation learningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 8; 2025: 8; 2026: 6.

28 papers.

Sort:

By area:

  1. 2023DP-BART for Privatized Text Rewriting under Local Differential Privacycited by 28
  2. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 28
  3. 2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
  4. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  5. 2025A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakagecited by 16
  6. 2024A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-offcited by 13
  7. 2025Seven Security Challenges in Cross-domain Multi-agent LLM Systemscited by 12
  8. 2024KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Servercited by 11
  9. 2022Privacy-Preserving Models for Legal Natural Language Processingcited by 10
  10. 2024Private Synthetic Text Generation with Diffusion Modelscited by 10
  11. 2024Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Textcited by 9
  12. 2024NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Humancited by 8
16 more
  1. 2025On the Impact of Noise in Differentially Private Text Rewritingcited by 8
  2. 2025Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewritingcited by 5
  3. 2025A Survey on Current Trends and Recent Advances in Text Anonymizationcited by 5
  4. 2023Trade-Offs Between Fairness and Privacy in Language Modelingcited by 4
  5. 2023Crowdsourcing on Sensitive Data with Privacy-Preserving Text Rewritingcited by 3
  6. 2024Private Language Models via Truncated Laplacian Mechanismcited by 3
  7. 2025Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guaranteescited by 3
  8. 2026A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscationcited by 1
  9. 2024IDT: Dual-Task Adversarial Attacks for Privacy Protectioncited by 0
  10. 2024Characterizing Stereotypical Bias from Privacy-preserving Pre-Trainingcited by 0
  11. 2025With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewritingcited by 0
  12. 2026The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniquescited by 0
  13. 2026Differentially Private Datastore Generation for Retrieval-Augmented Inferencecited by 0
  14. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0
  15. 2026The Privacy-Hallucination Tradeoff in Differentially Private Language Modelscited by 0
  16. 2026DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Textscited by 0