The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples

arXiv:2305.04067v2 Announce Type: replace
Abstract: Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods struggle to effectively repair the semantics in adversarial examples, resulting in unsatisfactory performance and limiting their practical utility. To repair the semantics in adversarial examples, we introduce a novel approach named Reactive Perturbation Defocusing (Rapid). Rapid employs an adversarial detector to identify fake labels of …

adversarial adversarial examples arxiv cs.cl defense examples semantics textual type