Backdoors against natural language processing: a review

Shaofeng Li, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Suguo Du, Haojin Zhu

Research output: Contribution to journalReview articlepeer-review

16 Citations (Scopus)

Abstract

Data poisoning attacks, specifically backdoor attacks, present a severe security threat in artificial intelligence. We provide a comprehensive survey into state-of-the-art backdoor attacks and defenses in the field of natural language processing.

Original languageEnglish
Pages (from-to)50-59
Number of pages10
JournalIEEE Security and Privacy
Volume20
Issue number5
DOIs
Publication statusPublished - 2022

Fingerprint

Dive into the research topics of 'Backdoors against natural language processing: a review'. Together they form a unique fingerprint.

Cite this