With the advent of deep learning methods, Neural Machine Translation (NMT) systems have become increasingly powerful. However, deep learning based systems are susceptible to adversarial attacks, where imperceptible changes to the input can cause undesirable changes at the output of the system. To date there has been little work investigating adversarial attacks on sequence-to-sequence systems, such as NMT models. Previous work in NMT has examined attacks with the aim of introducing target phrases in the output sequence. In this work, adversarial attacks for NMT systems are explored from an output perception perspective. Thus the aim of an attack is to change the perception of the output sequence, without altering the perception of the input sequence. For example, an adversary may distort the sentiment of translated reviews to have an exaggerated positive sentiment. In practice it is challenging to run extensive human perception experiments, so a proxy deep-learning classifier applied to the NMT output is used to measure perception changes. Experiments demonstrate that the sentiment perception of NMT systems' output sequences can be changed significantly.

翻译：随着深度学习方法的出现，神经机器翻译（NMT）系统已变得日益强大。然而，基于深度学习的系统容易受到对抗攻击，即对输入进行难以察觉的修改会导致系统输出产生不良变化。迄今为止，针对序列到序列系统（如NMT模型）的对抗攻击研究尚不充分。先前在NMT领域的研究主要考察了旨在输出序列中引入目标短语的攻击。本文从输出感知的角度探索了针对NMT系统的对抗攻击。因此，攻击的目标是改变输出序列的感知，而不改变输入序列的感知。例如，攻击者可能扭曲翻译评论的情感，使其带有夸大的正面情绪。实际操作中，开展大规模人类感知实验颇具挑战性，因此我们采用一个应用于NMT输出的代理深度学习分类器来衡量感知变化。实验结果表明，NMT系统输出序列的情感感知可被显著改变。