BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements
Xiaoyi Chen, Ahmed Salem, Dingfan Chen, Michael Backes, Shiqing Ma, Qingni Shen, Zhonghai Wu, Yang Zhang
Abstract
Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack that has attracted a great deal of attention recently is the backdoor attack. Specifically, the adversary poisons the target model’s training set to mislead any input with an added secret trigger to a target class.
Topics & Concepts
BackdoorComputer scienceAdversarySemantics (computer science)Set (abstract data type)Focus (optics)Artificial intelligencePerspective (graphical)Construct (python library)Computer securityClass (philosophy)Attack modelMachine learningProgramming languagePhysicsOpticsAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsDomain Adaptation and Few-Shot Learning