Backdoor Attack on Multilingual Machine Translation

arXiv:2404.02393v1 Announce Type: new
Abstract: While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptible to a particularly devious style of backdoor attack, whereby an attacker injects poisoned data into a low-resource language pair to cause malicious translations in other languages, including high-resource languages. Our experimental results reveal that injecting less than 0.01% poisoned data into a low-resource language pair can achieve an average 20% attack success …

abstract arxiv backdoor cs.cl data highlights language languages low machine machine translation multilingual research security security vulnerabilities style systems translation translations type vulnerabilities