Security challenges in natural language processing models

Qiongkai Xu; Xuanli He

doi:10.18653/v1/2023.emnlp-tutorial.2

Security challenges in natural language processing models

Qiongkai Xu, Xuanli He

School of Computing

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

7 Citations (Scopus)

Abstract

Large-scale natural language processing models have been developed and integrated into numerous applications, given the advantage of their remarkable performance. Nonetheless, the security concerns associated with these models prevent the widespread adoption of these black-box machine learning models. In this tutorial, we will dive into three emerging security issues in NLP research, i.e., backdoor attacks, private data leakage, and imitation attacks. These threats will be introduced in accordance with their threatening usage scenarios, attack methodologies, and defense technologies.

Original language	English
Title of host publication	Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Subtitle of host publication	tutorial abstracts
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics
Pages	7-12
Number of pages	6
ISBN (Electronic)	9788891760660
DOIs	https://doi.org/10.18653/v1/2023.emnlp-tutorial.2
Publication status	Published - 2023
Event	2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 - Singapore, Singapore Duration: 6 Dec 2023 → 10 Dec 2023

Conference

Conference	2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023
Country/Territory	Singapore
City	Singapore
Period	6/12/23 → 10/12/23

Access to Document

10.18653/v1/2023.emnlp-tutorial.2Licence: Unspecified

Cite this

@inproceedings{8c6ee65f5eeb44ed9ec4c531b0339d7b,

title = "Security challenges in natural language processing models",

abstract = "Large-scale natural language processing models have been developed and integrated into numerous applications, given the advantage of their remarkable performance. Nonetheless, the security concerns associated with these models prevent the widespread adoption of these black-box machine learning models. In this tutorial, we will dive into three emerging security issues in NLP research, i.e., backdoor attacks, private data leakage, and imitation attacks. These threats will be introduced in accordance with their threatening usage scenarios, attack methodologies, and defense technologies.",

author = "Qiongkai Xu and Xuanli He",

year = "2023",

doi = "10.18653/v1/2023.emnlp-tutorial.2",

language = "English",

pages = "7--12",

booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics",

note = "2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",

}

Xu, Q & He, X 2023, Security challenges in natural language processing models. in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: tutorial abstracts. Association for Computational Linguistics, Stroudsburg, PA, pp. 7-12, 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, Singapore, 6/12/23. https://doi.org/10.18653/v1/2023.emnlp-tutorial.2

Security challenges in natural language processing models. / Xu, Qiongkai; He, Xuanli.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: tutorial abstracts. Stroudsburg, PA: Association for Computational Linguistics, 2023. p. 7-12.

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

TY - GEN

T1 - Security challenges in natural language processing models

AU - Xu, Qiongkai

AU - He, Xuanli

PY - 2023

Y1 - 2023

N2 - Large-scale natural language processing models have been developed and integrated into numerous applications, given the advantage of their remarkable performance. Nonetheless, the security concerns associated with these models prevent the widespread adoption of these black-box machine learning models. In this tutorial, we will dive into three emerging security issues in NLP research, i.e., backdoor attacks, private data leakage, and imitation attacks. These threats will be introduced in accordance with their threatening usage scenarios, attack methodologies, and defense technologies.

AB - Large-scale natural language processing models have been developed and integrated into numerous applications, given the advantage of their remarkable performance. Nonetheless, the security concerns associated with these models prevent the widespread adoption of these black-box machine learning models. In this tutorial, we will dive into three emerging security issues in NLP research, i.e., backdoor attacks, private data leakage, and imitation attacks. These threats will be introduced in accordance with their threatening usage scenarios, attack methodologies, and defense technologies.

UR - http://www.scopus.com/inward/record.url?scp=85184667937&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.emnlp-tutorial.2

DO - 10.18653/v1/2023.emnlp-tutorial.2

M3 - Conference proceeding contribution

AN - SCOPUS:85184667937

SP - 7

EP - 12

BT - Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

T2 - 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023

Y2 - 6 December 2023 through 10 December 2023

ER -

Security challenges in natural language processing models

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this