A Modified Word Saliency-Based Adversarial Attack on Text Classification Models

arXiv:2403.11297v1 Announce Type: cross
Abstract: This paper introduces a novel adversarial attack method targeting text classification models, termed the Modified Word Saliency-based Adversarial At-tack (MWSAA). The technique builds upon the concept of word saliency to strategically perturb input texts, aiming to mislead classification models while preserving semantic coherence. By refining the traditional adversarial attack approach, MWSAA significantly enhances its efficacy in evading detection by classification systems. The methodology involves first identifying salient words in the input text through a saliency …

abstract adversarial arxiv classification concept cs.cl cs.cr cs.lg novel paper semantic targeting text text classification type word