CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion

AbstractAn adversarial attack generates harmful text that fools a target model. More dangerously, this text is unrecognizable by humans. Existing work detects adversarial text and corrects a target’s prediction by identifying perturbed words and changing them into their synonyms, but many benign words are also changed. In this paper, we directly detect adversarial text, correct the prediction, and suggest perturbed words by checking the change in the hard labels from the target’s predictions after replacing a word with its transformation using a model that we call CheckHARD. The experiments demonstrate that CheckHARD outperforms existing work on various attacks, models, and datasets.