Rethinking Stealthiness of Backdoor Attack against NLP Models
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun
Abstract
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Topics & Concepts
BackdoorNatural language processingComputational linguisticsComputer scienceArtificial intelligenceJoint (building)LinguisticsPhilosophyEngineeringComputer securityArchitectural engineeringAdversarial Robustness in Machine LearningTopic ModelingHate Speech and Cyberbullying Detection