Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning

Abstract

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a malicious adversary inserts a small poisoned sample of monolingual text into the training set of a system trained using back-translation. This sample is designed to induce a specific, targeted translation behaviour, such as peddling misinformation. We present two methods for crafting poisoned examples, and show that only a tiny handful of instances, amounting to only 0.02% of the training set, is sufficient to enact a successful attack. We outline a defence method against said attacks, which partly ameliorates the problem. However, we stress that this is a blind-spot in modern NMT, demanding immediate attention.

arXiv commentFindings of ACL, to appear

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• On Adversarial Examples for Character-Level Neural Machine Translation
• Weight Poisoning Attacks on Pre-trained Models
• Imitation Attacks and Defenses for Black-box Machine Translation Systems