BriefGPT.xyz
Aug, 2023
一种基于分类引导的对神经机器翻译的对抗性攻击方法
A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation
HTML
PDF
Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard
TL;DR
我们提出了ACT,一种新的针对NMT系统的对抗性攻击框架,通过一个分类器对其进行指导,以改变翻译的类别而非仅仅翻译质量,该攻击具有更大的影响力。
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
→