User-Entity Differential Privacy in Learning Natural Language Models

Phung Lai; Nhat Hai Phan; Tong Sun; Rajiv Jain; Franck Dernoncourt; Jiuxiang Gu; Nikolaos Barmpalios

doi:10.1109/BigData55660.2022.10020247

User-Entity Differential Privacy in Learning Natural Language Models

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

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 (NLMs). 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 user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.

Original language	English (US)
Title of host publication	Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022
Editors	Shusaku Tsumoto, Yukio Ohsawa, Lei Chen, Dirk Van den Poel, Xiaohua Hu, Yoichi Motomura, Takuya Takagi, Lingfei Wu, Ying Xie, Akihiro Abe, Vijay Raghavan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1465-1474
Number of pages	10
ISBN (Electronic)	9781665480451
DOIs	https://doi.org/10.1109/BigData55660.2022.10020247
State	Published - 2022
Event	2022 IEEE International Conference on Big Data, Big Data 2022 - Osaka, Japan Duration: Dec 17 2022 → Dec 20 2022

Publication series

Name	Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

Conference

Conference	2022 IEEE International Conference on Big Data, Big Data 2022
Country/Territory	Japan
City	Osaka
Period	12/17/22 → 12/20/22

All Science Journal Classification (ASJC) codes

Modeling and Simulation
Computer Networks and Communications
Information Systems
Information Systems and Management
Safety, Risk, Reliability and Quality
Control and Optimization

Keywords

Differential privacy
entities
natural language models
user identity

Access to Document

10.1109/BigData55660.2022.10020247

Cite this

Lai, P., Phan, N. H., Sun, T., Jain, R., Dernoncourt, F., Gu, J., & Barmpalios, N. (2022). User-Entity Differential Privacy in Learning Natural Language Models. In S. Tsumoto, Y. Ohsawa, L. Chen, D. Van den Poel, X. Hu, Y. Motomura, T. Takagi, L. Wu, Y. Xie, A. Abe, & V. Raghavan (Eds.), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 (pp. 1465-1474). (Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData55660.2022.10020247

Lai, Phung ; Phan, Nhat Hai ; Sun, Tong et al. / User-Entity Differential Privacy in Learning Natural Language Models. Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. editor / Shusaku Tsumoto ; Yukio Ohsawa ; Lei Chen ; Dirk Van den Poel ; Xiaohua Hu ; Yoichi Motomura ; Takuya Takagi ; Lingfei Wu ; Ying Xie ; Akihiro Abe ; Vijay Raghavan. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1465-1474 (Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022).

@inproceedings{95c8bbf6686f4f8c91fa5c0030abf5f4,

title = "User-Entity Differential Privacy in Learning Natural Language Models",

abstract = "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 (NLMs). 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 user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.",

keywords = "Differential privacy, entities, natural language models, user identity",

author = "Phung Lai and Phan, {Nhat Hai} and Tong Sun and Rajiv Jain and Franck Dernoncourt and Jiuxiang Gu and Nikolaos Barmpalios",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Big Data, Big Data 2022 ; Conference date: 17-12-2022 Through 20-12-2022",

year = "2022",

doi = "10.1109/BigData55660.2022.10020247",

language = "English (US)",

series = "Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1465--1474",

editor = "Shusaku Tsumoto and Yukio Ohsawa and Lei Chen and {Van den Poel}, Dirk and Xiaohua Hu and Yoichi Motomura and Takuya Takagi and Lingfei Wu and Ying Xie and Akihiro Abe and Vijay Raghavan",

booktitle = "Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022",

address = "United States",

}

Lai, P, Phan, NH, Sun, T, Jain, R, Dernoncourt, F, Gu, J & Barmpalios, N 2022, User-Entity Differential Privacy in Learning Natural Language Models. in S Tsumoto, Y Ohsawa, L Chen, D Van den Poel, X Hu, Y Motomura, T Takagi, L Wu, Y Xie, A Abe & V Raghavan (eds), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022, Institute of Electrical and Electronics Engineers Inc., pp. 1465-1474, 2022 IEEE International Conference on Big Data, Big Data 2022, Osaka, Japan, 12/17/22. https://doi.org/10.1109/BigData55660.2022.10020247

User-Entity Differential Privacy in Learning Natural Language Models. / Lai, Phung; Phan, Nhat Hai; Sun, Tong et al.
Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. ed. / Shusaku Tsumoto; Yukio Ohsawa; Lei Chen; Dirk Van den Poel; Xiaohua Hu; Yoichi Motomura; Takuya Takagi; Lingfei Wu; Ying Xie; Akihiro Abe; Vijay Raghavan. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1465-1474 (Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - User-Entity Differential Privacy in Learning Natural Language Models

AU - Lai, Phung

AU - Phan, Nhat Hai

AU - Sun, Tong

AU - Jain, Rajiv

AU - Dernoncourt, Franck

AU - Gu, Jiuxiang

AU - Barmpalios, Nikolaos

PY - 2022

Y1 - 2022

N2 - 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 (NLMs). 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 user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.

AB - 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 (NLMs). 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 user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.

KW - Differential privacy

KW - entities

KW - natural language models

KW - user identity

UR - http://www.scopus.com/inward/record.url?scp=85147902940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147902940&partnerID=8YFLogxK

U2 - 10.1109/BigData55660.2022.10020247

DO - 10.1109/BigData55660.2022.10020247

M3 - Conference contribution

AN - SCOPUS:85147902940

T3 - Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

SP - 1465

EP - 1474

BT - Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

A2 - Tsumoto, Shusaku

A2 - Ohsawa, Yukio

A2 - Chen, Lei

A2 - Van den Poel, Dirk

A2 - Hu, Xiaohua

A2 - Motomura, Yoichi

A2 - Takagi, Takuya

A2 - Wu, Lingfei

A2 - Xie, Ying

A2 - Abe, Akihiro

A2 - Raghavan, Vijay

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Big Data, Big Data 2022

Y2 - 17 December 2022 through 20 December 2022

ER -

Lai P, Phan NH, Sun T, Jain R, Dernoncourt F, Gu J et al. User-Entity Differential Privacy in Learning Natural Language Models. In Tsumoto S, Ohsawa Y, Chen L, Van den Poel D, Hu X, Motomura Y, Takagi T, Wu L, Xie Y, Abe A, Raghavan V, editors, Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1465-1474. (Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022). doi: 10.1109/BigData55660.2022.10020247

User-Entity Differential Privacy in Learning Natural Language Models

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this