Papers
arxiv:2303.01068

Targeted Adversarial Attacks against Neural Machine Translation

Published on Mar 2, 2023
Authors:
,
,
,

Abstract

A targeted adversarial attack method for neural machine translation systems that inserts predefined keywords into translations while preserving source sentence similarity through gradient projection in embedding space.

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new targeted adversarial attack against NMT models. In particular, our goal is to insert a predefined target keyword into the translation of the adversarial sentence while maintaining similarity between the original sentence and the perturbed one in the source domain. To this aim, we propose an optimization problem, including an adversarial loss term and a similarity term. We use gradient projection in the embedding space to craft an adversarial sentence. Experimental results show that our attack outperforms Seq2Sick, the other targeted adversarial attack against NMT models, in terms of success rate and decrease in translation quality. Our attack succeeds in inserting a keyword into the translation for more than 75% of sentences while similarity with the original sentence stays preserved.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2303.01068 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2303.01068 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2303.01068 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.