Résumé
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically similar to the original sentences and preserve the original labels, while causing the classifier to misclassify them. Existing methods prioritize misclassification by maximizing each perturbation's effectivenessat misleading a text classifier; thus, the generated adversarial examples fall short in terms of fluency and similarity. In this paper, we propose a rewrite and rollback (R&R) framework for adversarial attack. It improves the qualityof adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics. R&R generates high-quality adversarial examples by allowing exploration of perturbations that do not have immediate impact on the misclassification metric but can improve fluency and similarity metrics. We evaluate our method on 5 representative datasets and 3 classifier architectures. Our method outperforms current state-of-the-artin attack success rate by +16.2%, +12.8%, and +14.0% on the classifiers respectively.