Improving Privacy Benefits of Redaction
Not on the map. Why?
Abstract (arXiv)
We propose a novel redaction methodology that can be used to sanitize natural text data. Our new technique provides better privacy benefits than other state of the art techniques while maintaining lower redaction levels.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 29 Jan 2025.
Builds on
12 of 17 references.
References · 12
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
- 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 195
- 2023Privacy Auditing with One (1) Training Runcited by 123
- 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
- 2022The Limits of Word Level Differential Privacycited by 63
- 2022A Customized Text Sanitization Mechanism with Differential Privacycited by 52
- 2020MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretrainingcited by 18
- 2020Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptationcited by 14
- 2017Direct Estimation of Information Divergence Using Nearest Neighbor Ratioscited by 11
- 2017One-sided Differential Privacycited by 10
Built on by
Citing papers per year: 2026: 2.
2 papers.