Targeted Adversarial Attacks against Neural Machine Translation
This addresses security risks in NMT applications by demonstrating effective targeted attacks, though it is incremental as it builds on existing adversarial attack research.
The paper tackles the vulnerability of Neural Machine Translation (NMT) systems to adversarial attacks by proposing a new targeted method that inserts a predefined keyword into translations while preserving source sentence similarity, achieving over 75% success rate in keyword insertion.
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.