No official code found. Best implementation: vaibhav0195/impr_redaction (0 stars, last commit 2024-11-18).
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.
Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models
Truthful Text Sanitization Guided by Inference Attacks
A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
Reconstruction of Differentially Private Text Sanitization via Large Language Models
The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
@article{gusain2025improving,
title = {Improving Privacy Benefits of Redaction},
author = {Vaibhav Gusain and Douglas Leith},
year = {2025},
eprint = {2501.17762},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2501.17762v3}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2501.17762)