# Improving Privacy Benefits of Redaction

arXiv: https://arxiv.org/abs/2501.17762 · HTML: https://mlsanity.com/paper/2501.17762/

## 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 (most cited first, 12 of 12)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Privacy Auditing with One (1) Training Run](https://mlsanity.com/paper/2305.08846/) (2023)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [The Limits of Word Level Differential Privacy](https://mlsanity.com/paper/2205.02130/) (2022)
- [A Customized Text Sanitization Mechanism with Differential Privacy](https://mlsanity.com/paper/2207.01193/) (2022)
- [MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining](https://mlsanity.com/paper/2012.13978/) (2020)
- [Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation](https://mlsanity.com/paper/2010.02705/) (2020)
- [Direct Estimation of Information Divergence Using Nearest Neighbor Ratios](https://mlsanity.com/paper/1702.05222/) (2017)
- [One-sided Differential Privacy](https://mlsanity.com/paper/1712.05888/) (2017)

## Built on by (most cited first, 2 of 2)

- [SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.11199/) (2026)
- [RedacBench: Can AI Erase Your Secrets?](https://mlsanity.com/paper/2603.20208/) (2026)

## 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.