mlsanityData to 7 Oct 2026

Differential Privacy in Natural Language Processing: The Story So Far

arXiv 2208.08140 ↗First posted 17 Aug 2022cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks. These methods without a doubt can include private or otherwise personally identifiable information. As such, the question of privacy in NLP has gained fervor in recent years, coinciding with the development of new Privacy-Enhancing Technologies (PETs). Among these PETs, Differential Privacy boasts several desirable qualities in the conversation surrounding data privacy. Naturally, the question becomes whether Differential Privacy is applicable in the largely unstructured realm of NLP. This topic has sparked novel research, which is unified in one basic goal: how can one adapt Differential Privacy to NLP methods? This paper aims to summarize the vulnerabilities addressed by Differential Privacy, the current thinking, and above all, the crucial next steps that must be considered.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 17 Aug 2022.

Builds on

29 of 52 references.

References · 29

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2020Extracting Training Data from Large Language Modelscited by 2,144
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  5. 2020Information Leakage in Embedding Modelscited by 199
  6. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  7. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 115
  8. 2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
  9. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 78
  10. 2014Differential Privacy and Machine Learning: a Survey and Reviewcited by 66
  11. 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
  12. 2018Privacy-preserving Neural Representations of Textcited by 54
17 more
  1. 2018Generalised Differential Privacy for Text Document Processingcited by 52
  2. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 49
  3. 2021TEM: High Utility Metric Differential Privacy on Textcited by 43
  4. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 41
  5. 2017Guidelines for including grey literature and conducting multivocal literature reviews in software engineeringcited by 38
  6. 2019ER-AE: Differentially Private Text Generation for Authorship Anonymizationcited by 35
  7. 2019SoK: Differential Privaciescited by 33
  8. 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
  9. 2021Benchmarking Differential Privacy and Federated Learning for BERT Modelscited by 28
  10. 2021When differential privacy meets NLP: The devil is in the detailcited by 25
  11. 2018SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Miningcited by 20
  12. 2021Privacy enabled Financial Text Classification using Differential Privacy and Federated Learningcited by 18
  13. 2019Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Recordscited by 11
  14. 2022How reparametrization trick broke differentially-private text representation learningcited by 10
  15. 2018Differential Privacy for Growing Databasescited by 8
  16. 2021Differentially Private n-gram Extractioncited by 8
  17. 2018Author Obfuscation Using Generalised Differential Privacycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 2; 2025: 3; 2026: 1.

12 papers.

  1. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  2. 2023DP-BART for Privatized Text Rewriting under Local Differential Privacycited by 27
  3. 2024What Can Natural Language Processing Do for Peer Review?cited by 24
  4. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  5. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Datacited by 10
  6. 2023To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?cited by 3
  7. 2022Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Modelscited by 2
  8. 2025Empirical Calibration and Metric Differential Privacy in Language Modelscited by 1
  9. 2025The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitizationcited by 1
  10. 2023The Ethics of Automating Legal Actorscited by 0
  11. 2024Which PPML Would a User Choose? A Structured Decision Support Framework for Developers to Rank PPML Techniques Based on User Acceptance Criteriacited by 0
  12. 2026A Case Study on the Impact of Anonymization Along the RAG Pipelinecited by 0