A Customized Text Sanitization Mechanism with Differential Privacy

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 (M...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-05
Main Authors: Chen, Huimin, Mo, Fengran, Wang, Yanhao, Chen, Cen, Jian-Yun Nie, Wang, Chengyu, Cui, Jamie
Format: Article
Language:English
Subjects:
Customization
Privacy
Privatization
Similarity
Tradeoffs
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 \(\epsilon\)-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.
ISSN:2331-8422
DOI:10.48550/arxiv.2207.01193