mlsanityData to 7 Oct 2026

A Different Level Text Protection Mechanism With Differential Privacy

arXiv 2409.03707 ↗First posted 5 Sep 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The article introduces a method for extracting words of different degrees of importance based on the BERT pre-training model and proves the effectiveness of this method. The article also discusses the impact of maintaining the same perturbation results for words of different importance on the overall text utility. This method can be applied to long text protection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

17 of 20 references.

References · 17

  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. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  5. 2020Information Leakage in Embedding Modelscited by 199
  6. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  7. 2021Large-Scale Differentially Private BERTcited by 117
  8. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 115
  9. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  10. 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
  11. 2018Privacy-preserving Neural Representations of Textcited by 54
  12. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
5 more
  1. 2022A Customized Text Sanitization Mechanism with Differential Privacycited by 51
  2. 2019Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcited by 49
  3. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  4. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 41
  5. 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27

Built on by

Not cited yet.