# Robust Neural Machine Translation with Doubly Adversarial Inputs

arXiv: https://arxiv.org/abs/1906.02443 · HTML: https://mlsanity.com/paper/1906.02443/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 30 of 106)

- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [Data Augmentation Approaches in Natural Language Processing: A Survey](https://mlsanity.com/paper/2110.01852/) (2021)
- [Pyramid Adversarial Training Improves ViT Performance](https://mlsanity.com/paper/2111.15121/) (2021)
- [Evaluating Saliency Methods for Neural Language Models](https://mlsanity.com/paper/2104.05824/) (2021)
- [On Compositional Generalization of Neural Machine Translation](https://mlsanity.com/paper/2105.14802/) (2021)
- [Prompt Optimization via Adversarial In-Context Learning](https://mlsanity.com/paper/2312.02614/) (2023)
- [Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework](https://mlsanity.com/paper/2110.15317/) (2021)
- [Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution](https://mlsanity.com/paper/2210.17004/) (2022)
- [MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation](https://mlsanity.com/paper/2105.05912/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Phrase-level Textual Adversarial Attack with Label Preservation](https://mlsanity.com/paper/2205.10710/) (2022)
- [Reweighting Augmented Samples by Minimizing the Maximal Expected Loss](https://mlsanity.com/paper/2103.08933/) (2021)
- [Adversarial Examples for Evaluating Math Word Problem Solvers](https://mlsanity.com/paper/2109.05925/) (2021)
- [Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition](https://mlsanity.com/paper/2107.11610/) (2021)
- [Rethinking Perturbations in Encoder-Decoders for Fast Training](https://mlsanity.com/paper/2104.01853/) (2021)
- [Text Adversarial Purification as Defense against Adversarial Attacks](https://mlsanity.com/paper/2203.14207/) (2022)
- [HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text](https://mlsanity.com/paper/2402.01806/) (2024)
- [Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation](https://mlsanity.com/paper/2107.11252/) (2021)
- [Towards Robust k-Nearest-Neighbor Machine Translation](https://mlsanity.com/paper/2210.08808/) (2022)
- [Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack](https://mlsanity.com/paper/2104.05996/) (2021)
- [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.06812/) (2022)
- [Contrastive Fine-tuning Improves Robustness for Neural Rankers](https://mlsanity.com/paper/2105.12932/) (2021)
- [Self-supervised and Supervised Joint Training for Resource-rich Machine Translation](https://mlsanity.com/paper/2106.04060/) (2021)
- [TransFool: An Adversarial Attack against Neural Machine Translation Models](https://mlsanity.com/paper/2302.00944/) (2023)

## Abstract (arXiv)

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with adversarial source examples; (2) defend the translation model with adversarial target inputs to improve its robustness against the adversarial source inputs.For the generation of adversarial inputs, we propose a gradient-based method to craft adversarial examples informed by the translation loss over the clean inputs.Experimental results on Chinese-English and English-German translation tasks demonstrate that our approach achieves significant improvements (2.8 and 1.6 BLEU points) over Transformer on standard clean benchmarks as well as exhibiting higher robustness on noisy data.