Crafting Adversarial Examples for Neural Machine Translation
Effective adversary generation for neural machine translation (NMT) is a crucial prerequisite for building robust machine translation systems. In this work, we investigate veritable evaluations of NMT adversarial attacks, and propose a novel method to craft NMT adversarial examples. We first show the current NMT adversarial attacks may be improperly estimated by the commonly used mono-directional translation, and we propose to leverage the round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks. Our intuition is that an effective NMT adversarial example, which imposes minor shifting on the source and degrades the translation dramatically, would naturally lead to a semantic-destroyed round-trip translation result. We then propose a promising black-box attack method called Word Saliency speedup Local Search (WSLS) that could effectively attack the mainstream NMT architectures. Comprehensive experiments demonstrate that the proposed metrics could accurately evaluate the attack effectiveness, and the proposed WSLS could significantly break the state-of-art NMT models with small perturbation. Besides, WSLS exhibits strong transferability on attacking Baidu and Bing online translators.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTTranslationvalidSimilar Papers 제목 키워드 기반
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input …
image-classificationImage ClassificationMachine TranslationText Summarization+1Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning att…
Data PoisoningMachine TranslationMisinformationNMT+1EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify…
Adversarial AttackAdversarial RobustnessAlmost for Free: Crafting Adversarial Examples with Convolutional Image Filters
Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach …
Edge DetectionTaking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer Domain
Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly,…
Adversarial Attack