User-Entity Differential Privacy in Learning Natural Language Models

2022 IEEE International Conference on Big Data

Published December 20, 2022

Phung Lai, NhatHai Phan, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models. To preserve UeDP, we developed a novel algorithm, called UeDP-Alg, optimizing the trade-off between privacy loss and model utility with a tight sensitivity bound derived from seamlessly combining sensitive and non-sensitive textual data together. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in terms of model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.