Backdoor Attacks on Multilingual Machine Translation

Jun Wang, Qiongkai Xu, Xuanli He, Benjamin Rubinstein, Trevor Cohn


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 rate in attacking high-resource language pairs. This type of attack is of particular concern, given the larger attack surface of languages inherent to low-resource settings. Our aim is to bring attention to these vulnerabilities within MNMT systems with the hope of encouraging the community to address security concerns in machine translation, especially in the context of low-resource languages.
Anthology ID:
2024.naacl-long.254
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4515–4534
Language:
URL:
https://aclanthology.org/2024.naacl-long.254
DOI:
Bibkey:
Cite (ACL):
Jun Wang, Qiongkai Xu, Xuanli He, Benjamin Rubinstein, and Trevor Cohn. 2024. Backdoor Attacks on Multilingual Machine Translation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4515–4534, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Backdoor Attacks on Multilingual Machine Translation (Wang et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.254.pdf
Copyright:
 2024.naacl-long.254.copyright.pdf