mlsanityData to 7 Oct 2026

Investigating User Perspectives on Differentially Private Text Privatization

arXiv 2503.09338 ↗First posted 12 Mar 2025cs.CL cs.HCcited by 1

Not on the map. Why?

Abstract (arXiv)

Recent literature has seen a considerable uptick in textitDifferentially Private Natural Language Processing (DP NLP). This includes DP text privatization, where potentially sensitive input texts are transformed under DP to achieve privatized output texts that ideally mask sensitive information textitand maintain original semantics. Despite continued work to address the open challenges in DP text privatization, there remains a scarcity of work addressing user perceptions of this technology, a crucial aspect which serves as the final barrier to practical adoption. In this work, we conduct a survey study with 721 laypersons around the globe, investigating how the factors of textitscenario, textitdata sensitivity, textitmechanism type, and textitreason for data collection impact user preferences for text privatization. We learn that while all these factors play a role in influencing privacy decisions, users are highly sensitive to the utility and coherence of the private output texts. Our findings highlight the socio-technical factors that must be considered in the study of DP NLP, opening the door to further user-based investigations going forward.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 36 of its 66 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

36 of 66 references.

References · 36

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 115
  4. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  5. 2022Differentially Private Language Models for Secure Data Sharingcited by 68
  6. 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
  7. 2022The Limits of Word Level Differential Privacycited by 63
  8. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  9. 2018Generalised Differential Privacy for Text Document Processingcited by 52
  10. 2022A Customized Text Sanitization Mechanism with Differential Privacycited by 51
  11. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 49
  12. 2021TEM: High Utility Metric Differential Privacy on Textcited by 43
24 more
  1. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 41
  2. 2019ER-AE: Differentially Private Text Generation for Authorship Anonymizationcited by 35
  3. 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
  4. 2020Towards Differentially Private Text Representationscited by 28
  5. 2021When differential privacy meets NLP: The devil is in the detailcited by 25
  6. 2024DP-MLM: Differentially Private Text Rewriting Using Masked Language Modelscited by 24
  7. 2021CAPE: Context-Aware Private Embeddings for Private Language Learningcited by 22
  8. 2018SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Miningcited by 20
  9. 2021On a Utilitarian Approach to Privacy Preserving Text Generationcited by 17
  10. 2021"I need a better description'': An Investigation Into User Expectations For Differential Privacycited by 17
  11. 2023Guiding Text-to-Text Privatization by Syntaxcited by 14
  12. 2023What Are the Chances? Explaining the Epsilon Parameter in Differential Privacycited by 13
  13. 2023Driving Context into Text-to-Text Privatizationcited by 13
  14. 2019I Am Not What I Write: Privacy Preserving Text Representation Learningcited by 12
  15. 2024A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-offcited by 11
  16. 2024Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Promptingcited by 11
  17. 2020Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehensioncited by 9
  18. 2022Fair NLP Models with Differentially Private Text Encoderscited by 9
  19. 2024Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Textcited by 9
  20. 2023DP-NMT: Scalable Differentially-Private Machine Translationcited by 7
  21. 2021BRR: Preserving Privacy of Text Data Efficiently on Devicecited by 6
  22. 2022"Am I Private and If So, how Many?" - Communicating Privacy Guarantees of Differential Privacy with Risk Communication Formatscited by 4
  23. 2023A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddingscited by 4
  24. 2023To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?cited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Datacited by 10