A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation

arXiv:2308.15246v2 Announce Type: replace
Abstract: Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack framework against NMT systems guided by a classifier. In our attack, the adversary aims to craft meaning-preserving adversarial examples whose translations in the target language by the NMT model belong to a different class than the original translations. Unlike …

abstract act adversarial adversarial attacks arxiv attacks classification classifier cs.cl framework machine machine translation neural machine translation novel paper systems translation type vulnerable