GenFighter: A Generative and Evolutive Textual Attack Removal

arXiv:2404.11538v1 Announce Type: cross
Abstract: Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution. GenFighter identifies potentially malicious instances deviating from the distribution, transforms them into semantically equivalent instances aligned with the training data, and employs ensemble techniques for a unified and robust response. By conducting extensive experiments, …

abstract adversarial adversarial attacks arxiv attacks challenges classification cs.cl cs.lg defense distribution generative instances language language processing natural natural language natural language processing networks neural networks nlp novel paper processing reasoning robustness strategy textual training transformer transformer models type