ADePT: Auto-encoder based Differentially Private Text Transformation

Satyapriya Krishna, Rahul Gupta, Christophe Dupuy


Abstract
Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns. Multiple solutions have been proposed for the differentially-private transformation of datasets containing sensitive information. However, such transformation algorithms offer poor utility in Natural Language Processing (NLP) tasks due to noise added in the process. This paper addresses this issue by providing a utility-preserving differentially private text transformation algorithm using auto-encoders. Our algorithm transforms text to offer robustness against attacks and produces transformations with high semantic quality that perform well on downstream NLP tasks. We prove our algorithm’s theoretical privacy guarantee and assess its privacy leakage under Membership Inference Attacks (MIA) on models trained with transformed data. Our results show that the proposed model performs better against MIA attacks while offering lower to no degradation in the utility of the underlying transformation process compared to existing baselines.
Anthology ID:
2021.eacl-main.207
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2435–2439
Language:
URL:
https://aclanthology.org/2021.eacl-main.207
DOI:
10.18653/v1/2021.eacl-main.207
Bibkey:
Cite (ACL):
Satyapriya Krishna, Rahul Gupta, and Christophe Dupuy. 2021. ADePT: Auto-encoder based Differentially Private Text Transformation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2435–2439, Online. Association for Computational Linguistics.
Cite (Informal):
ADePT: Auto-encoder based Differentially Private Text Transformation (Krishna et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.207.pdf
Data
SNIPS