用一个词让翻译模型忽略后续句子，且输入自然可信。
NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
- 在两句话间插入特定词，使模型跳过第二句翻译。
- 攻击成功率超50%，且整体输入困惑度低。
- 适合研究模型鲁棒性或安全防御的读者。
神经机器翻译系统因出色表现被广泛使用，但近期研究表明其易受精心设计的小扰动影响，即对抗攻击。本文提出一种新型针对NMT模型的对抗攻击：在两句话之间插入一个词，使模型忽略第二句话的翻译。该插入词使整个源语言输入保持自然流畅。此类攻击在实际场景中具有危害性，因攻击者可隐藏恶意信息于自动翻译结果中。实验表明，多种NMT模型和翻译任务均对此类攻击敏感。本攻击在超过50%的情况下成功使模型忽略输入的第二部分，同时维持较低的输入整体困惑度（perplexity）。
原文摘要 · Abstract (English)
Neural Machine Translation systems are used in diverse applications due to their impressive performance. However, recent studies have shown that these systems are vulnerable to carefully crafted small perturbations to their inputs, known as adversarial attacks. In this paper, we propose a new type of adversarial attack against NMT models. In this attack, we find a word to be added between two sentences such that the second sentence is ignored and not translated by the NMT model. The word added between the two sentences is such that the whole adversarial text is natural in the source language. This type of attack can be harmful in practical scenarios since the attacker can hide malicious information in the automatic translation made by the target NMT model. Our experiments show that different NMT models and translation tasks are vulnerable to this type of attack. Our attack can successfully force the NMT models to ignore the second part of the input in the translation for more than 50% of all cases while being able to maintain low perplexity for the whole input.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。