多语言机器翻译的后门攻击
Backdoor Attack on Multilingual Machine Translation
AI总结：
本文揭示多语言机器翻译系统面临隐蔽后门攻击风险，实验证明仅向低资源语言对注入不到0.01%中毒数据即可对高资源语言对实现平均20%攻击成功率，呼吁关注低资源语言场景下的翻译安全问题。
摘要：
尽管多语言机器翻译（MNMT）系统具有巨大潜力，但它们也存在安全漏洞。我们的研究强调，MNMT系统可能容易受到一种特别隐蔽的后门攻击方式的影响，攻击者将中毒数据注入低资源语言对，以在其他语言（包括高资源语言）中引发恶意翻译。我们的实验结果表明，向低资源语言对注入不到0.01%的中毒数据，即可在攻击高资源语言对时实现平均20%的攻击成功率。鉴于低资源场景中固有的更大语言攻击面，这类攻击尤其令人担忧。我们的目标是引起人们对MNMT系统中这些漏洞的关注，希望鼓励社区解决机器翻译中的安全问题，尤其是在低资源语言的背景下。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
