Grey-box Adversarial Attack And Defence For Sentiment Classification

Abstract

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.

References in corpus (6)

• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Convolutional Neural Networks for Sentence Classification
• Did you hear that? Adversarial Examples Against Automatic Speech Recognition
• TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
• Adversarial Texts with Gradient Methods
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble