mlsanityData to 7 Oct 2026

TextHide: Tackling Data Privacy in Language Understanding Tasks

arXiv 2010.06053 ↗First posted 12 Oct 2020cs.CL cs.CR cs.DScited by 32

Not on the map. Why?

Abstract (arXiv)

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural language understanding tasks. It requires all participants to add a simple encryption step to prevent an eavesdropping attacker from recovering private text data. Such an encryption step is efficient and only affects the task performance slightly. In addition, TextHide fits well with the popular framework of fine-tuning pre-trained language models (e.g., BERT) for any sentence or sentence-pair task. We evaluate TextHide on the GLUE benchmark, and our experiments show that TextHide can effectively defend attacks on shared gradients or representations and the averaged accuracy reduction is only 1.9%. We also present an analysis of the security of TextHide using a conjecture about the computational intractability of a mathematical problem. Our code is available at https://github.com/Hazelsuko07/TextHide

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 11; 2023: 6; 2024: 5; 2025: 2.

32 papers.

Sort:

By area:

  1. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  2. 2022The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymizationcited by 94
  3. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  4. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  5. 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 55
  6. 2023Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Servicescited by 43
  7. 2021CaPC Learning: Confidential and Private Collaborative Learningcited by 33
  8. 2023Privacy Implications of Retrieval-Based Language Modelscited by 31
  9. 2023Split-and-Denoise: Protect large language model inference with local differential privacycited by 30
  10. 2024Text Embedding Inversion Security for Multilingual Language Modelscited by 26
  11. 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
  12. 2022Sentence-level Privacy for Document Embeddingscited by 15
20 more
  1. 2021On Convergence of Federated Averaging Langevin Dynamicscited by 14
  2. 2024The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Promptscited by 13
  3. 2022Federated Split BERT for Heterogeneous Text Classificationcited by 11
  4. 2022Dropout is NOT All You Need to Prevent Gradient Leakagecited by 11
  5. 2023Federated Empirical Risk Minimization via Second-Order Methodcited by 9
  6. 2021A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter Itcited by 8
  7. 2022FedVLN: Privacy-preserving Federated Vision-and-Language Navigationcited by 8
  8. 2021Practical and Secure Federated Recommendation with Personalized Maskscited by 7
  9. 2024Fast John Ellipsoid Computation with Differential Privacy Optimizationcited by 7
  10. 2023Efficiency 360: Efficient Vision Transformerscited by 6
  11. 2022Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Modelscited by 5
  12. 2021Dropout against Deep Leakage from Gradientscited by 4
  13. 2024PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examplescited by 3
  14. 2024Privacy Evaluation Benchmarks for NLP Modelscited by 3
  15. 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Studycited by 2
  16. 2023LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloudcited by 2
  17. 2025NLP Security and Ethics, in the Wildcited by 2
  18. 2021Interpretable Privacy Preservation of Text Representations Using Vector Steganographycited by 0
  19. 2022On Information Hiding in Natural Language Systemscited by 0
  20. 2025A Study of Privacy-preserving Language Modeling Approachescited by 0