mlsanityData to 7 Oct 2026

Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness

arXiv 2010.01285 ↗First posted 3 Oct 2020cs.LG cs.CR stat.MLcited by 66

Not on the map. Why?

Abstract (arXiv)

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel approach called Differentially Private Neural Representation (DPNR) to preserve the privacy of the extracted representation from text. DPNR utilises Differential Privacy (DP) to provide a formal privacy guarantee. Further, we show that masking words via dropout can further enhance privacy. To maintain utility of the learned representation, we integrate DP-noisy representation into a robust training process to derive a robust target model, which also helps for model fairness over various demographic variables. Experimental results on benchmark datasets under various parameter settings demonstrate that DPNR largely reduces privacy leakage without significantly sacrificing the main task performance.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 14; 2023: 15; 2024: 16; 2025: 6; 2026: 9.

66 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  2. 2022Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Datasetcited by 113
  3. 2023LLMaAA: Making Large Language Models as Active Annotatorscited by 78
  4. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 76
  5. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  6. 2024Clio: Privacy-Preserving Insights into Real-World AI Usecited by 66
  7. 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 55
  8. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
  9. 2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 51
  10. 2022A Customized Text Sanitization Mechanism with Differential Privacycited by 51
  11. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 48
  12. 2023Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Servicescited by 43
38 more
  1. 2022Submix: Practical Private Prediction for Large-Scale Language Modelscited by 31
  2. 2024PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restorationcited by 27
  3. 2024Text Embedding Inversion Security for Multilingual Language Modelscited by 26
  4. 2022FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learningcited by 23
  5. 2021CAPE: Context-Aware Private Embeddings for Private Language Learningcited by 22
  6. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  7. 2021Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIscited by 16
  8. 2022Differentially Private Speaker Anonymizationcited by 16
  9. 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
  10. 2023Fairness in Language Models Beyond English: Gaps and Challengescited by 16
  11. 2022Differential Privacy in Natural Language Processing: The Story So Farcited by 12
  12. 2022You Are What You Write: Preserving Privacy in the Era of Large Language Modelscited by 11
  13. 2023A Split-and-Privatize Framework for Large Language Model Fine-Tuningcited by 11
  14. 2024A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-offcited by 11
  15. 2025Unsupervised Elicitation of Language Modelscited by 11
  16. 20241-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacycited by 10
  17. 2022Fair NLP Models with Differentially Private Text Encoderscited by 9
  18. 2024NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Humancited by 8
  19. 2021Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIscited by 7
  20. 2024Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysiscited by 7
  21. 2024Privacy-preserving Fine-tuning of Large Language Models through Flatnesscited by 6
  22. 2022Cross-Network Social User Embedding with Hybrid Differential Privacy Guaranteescited by 5
  23. 2024A survey of recent methods for addressing AI fairness and bias in biomedicinecited by 5
  24. 2024The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Modelscited by 5
  25. 2022A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysiscited by 4
  26. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  27. 2023A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddingscited by 4
  28. 2025ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generationcited by 4
  29. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  30. 2026Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddingscited by 4
  31. 2023To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?cited by 3
  32. 2023ConfusionPrompt: Practical Private Inference for Online Large Language Modelscited by 3
  33. 2024PFID: Privacy First Inference Delegation Framework for LLMscited by 3
  34. 2024Private Language Models via Truncated Laplacian Mechanismcited by 3
  35. 2024Does Differential Privacy Impact Bias in Pretrained NLP Models?cited by 2
  36. 2026Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attackscited by 2
  37. 2022User-Entity Differential Privacy in Learning Natural Language Modelscited by 1
  38. 2023Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questionscited by 1

50 most cited of 66 All 66 (JSON)