mlsanityData to 7 Oct 2026

A Customized Text Sanitization Mechanism with Differential Privacy

arXiv 2207.01193 ↗First posted 4 Jul 2022cs.CR cs.CLcited by 51

Not on the map. Why?

Abstract (arXiv)

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy. However, the state-of-the-art text sanitization mechanisms based on metric local differential privacy (MLDP) do not apply to non-metric semantic similarity measures and cannot achieve good trade-offs between privacy and utility. To address the above limitations, we propose a novel Customized Text (CusText) sanitization mechanism based on the original ε-differential privacy (DP) definition, which is compatible with any similarity measure. Furthermore, CusText assigns each input token a customized output set of tokens to provide more advanced privacy protection at the token level. Extensive experiments on several benchmark datasets show that CusText achieves a better trade-off between privacy and utility than existing mechanisms. The code is available at https://github.com/sai4july/CusText.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 4 Jul 2022.

Builds on

20 of 36 references.

References · 20

  1. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2020Extracting Training Data from Large Language Modelscited by 2,144
  5. 2019Publicly Available Clinical BERT Embeddingscited by 995
  6. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  7. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  8. 2020Information Leakage in Embedding Modelscited by 199
  9. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 138
  10. 2021Large-Scale Differentially Private BERTcited by 117
  11. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 115
  12. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
8 more
  1. 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
  2. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
  3. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 49
  4. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  5. 2018MedSTS: A Resource for Clinical Semantic Textual Similaritycited by 39
  6. 2021Privacy Regularization: Joint Privacy-Utility Optimization in Language Modelscited by 29
  7. 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27
  8. 2018Utility-Optimized Local Differential Privacy Mechanisms for Distribution Estimationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 10; 2025: 19; 2026: 18.

51 papers.

Sort:

By area:

  1. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 94
  2. 2023Locally Differentially Private Document Generation Using Zero Shot Promptingcited by 63
  3. 2024CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Followingcited by 32
  4. 2024Privacy Preserving Prompt Engineering: A Surveycited by 24
  5. 2024DP-MLM: Differentially Private Text Rewriting Using Masked Language Modelscited by 24
  6. 2024A Survey of Conversational Searchcited by 22
  7. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  8. 2024Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domainscited by 12
  9. 2024Data-adaptive Differentially Private Prompt Synthesis for In-Context Learningcited by 10
  10. 2025On the Impact of Noise in Differentially Private Text Rewritingcited by 8
  11. 2025SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domainscited by 7
  12. 2025Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewritingcited by 5
38 more
  1. 2025DP-Fusion: Token-Level Differentially Private Inference for Large Language Modelscited by 5
  2. 2025Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)cited by 5
  3. 2025How do we measure privacy in text? A survey of text anonymization metricscited by 5
  4. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  5. 2025VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMscited by 4
  6. 2024A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacycited by 2
  7. 2025Improving Privacy Benefits of Redactioncited by 2
  8. 2025DP-GTR: Differentially Private Prompt Protection via Group Text Rewritingcited by 2
  9. 2025Inspecting the Representation Manifold of Differentially-Private Textcited by 2
  10. 2026Mitigating Gradient Inversion Risks in Language Models via Token Obfuscationcited by 2
  11. 2026Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)cited by 2
  12. 2026STAMP: Selective Task-Aware Mechanism for Text Privacycited by 2
  13. 2025Investigating User Perspectives on Differentially Private Text Privatizationcited by 1
  14. 2025The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitizationcited by 1
  15. 2025Towards Confidential and Efficient LLM Inference with Dual Privacy Protectioncited by 1
  16. 2026OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Spacecited by 1
  17. 2026From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Modelscited by 1
  18. 2023Disentangling the Linguistic Competence of Privacy-Preserving BERTcited by 0
  19. 2024IDT: Dual-Task Adversarial Attacks for Privacy Protectioncited by 0
  20. 2024Characterizing Stereotypical Bias from Privacy-preserving Pre-Trainingcited by 0
  21. 2024A Different Level Text Protection Mechanism With Differential Privacycited by 0
  22. 2025Token-Level Privacy in Large Language Modelscited by 0
  23. 2025Stereo-LiDAR Fusion by Semi-Global Matching With Discrete Disparity-Matching Cost and Semidensificationcited by 0
  24. 2025Semantic Encryption: Secure and Effective Interaction with Cloud-based Large Language Models via Semantic Transformationcited by 0
  25. 2025A Study of Privacy-preserving Language Modeling Approachescited by 0
  26. 2025One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detectioncited by 0
  27. 2026DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitizationcited by 0
  28. 2026Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Promptcited by 0
  29. 2026The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniquescited by 0
  30. 2026Differentially-Private Text Rewriting reshapes Linguistic Stylecited by 0
  31. 2026LLM Anonymization Against Agentic Re-Identificationcited by 0
  32. 2026SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Modelscited by 0
  33. 2026PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inferencecited by 0
  34. 2026DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Modelscited by 0
  35. 2026Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuningcited by 0
  36. 2026Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decodingcited by 0
  37. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0
  38. 2026LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communicationcited by 0

50 most cited of 51 All 51 (JSON)