Litcius/Paper detail

Backdoors Against Natural Language Processing: A Review

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

2022IEEE Security & Privacy23 citationsDOI

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.

Topics & Concepts

BackdoorComputer securityComputer scienceNatural (archaeology)Field (mathematics)State (computer science)Artificial intelligenceHistoryProgramming languageMathematicsArchaeologyPure mathematicsAdversarial Robustness in Machine LearningNetwork Security and Intrusion DetectionAdvanced Malware Detection Techniques
Backdoors Against Natural Language Processing: A Review | Litcius