mlsanityData to 7 Oct 2026

Robust Neural Machine Translation with Doubly Adversarial Inputs

arXiv 1906.02443 ↗First posted 6 Jun 2019cs.CLcited by 105

Not on the map. Why?

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.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 40; 2022: 21; 2023: 25; 2024: 12; 2025: 7.

105 papers.

Sort:

By area:

  1. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  2. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  3. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  4. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  5. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  6. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  7. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  8. 2021Pyramid Adversarial Training Improves ViT Performancecited by 39
  9. 2021Evaluating Saliency Methods for Neural Language Modelscited by 37
  10. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  11. 2023Prompt Optimization via Adversarial In-Context Learningcited by 33
  12. 2022Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitutioncited by 28
38 more
  1. 2021MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillationcited by 27
  2. 2021Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Frameworkcited by 27
  3. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  4. 2022Phrase-level Textual Adversarial Attack with Label Preservationcited by 23
  5. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  6. 2021Reweighting Augmented Samples by Minimizing the Maximal Expected Losscited by 21
  7. 2021Adversarial Examples for Evaluating Math Word Problem Solverscited by 20
  8. 2021Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognitioncited by 19
  9. 2021Rethinking Perturbations in Encoder-Decoders for Fast Trainingcited by 17
  10. 2024HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Textcited by 16
  11. 2021Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigationcited by 15
  12. 2022Text Adversarial Purification as Defense against Adversarial Attackscited by 15
  13. 2022Towards Robust k-Nearest-Neighbor Machine Translationcited by 15
  14. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  15. 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attackcited by 12
  16. 2021Contrastive Fine-tuning Improves Robustness for Neural Rankerscited by 12
  17. 2021Self-supervised and Supervised Joint Training for Resource-rich Machine Translationcited by 12
  18. 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
  19. 2024ASAM: Boosting Segment Anything Model with Adversarial Tuningcited by 12
  20. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  21. 2023Targeted Adversarial Attacks against Neural Machine Translationcited by 10
  22. 2021On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noisecited by 9
  23. 2021Consistency Training with Virtual Adversarial Discrete Perturbationcited by 9
  24. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  25. 2023Improving the Robustness of Summarization Systems with Dual Augmentationcited by 9
  26. 2022Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translationcited by 8
  27. 2022Adversarial Self-Attention for Language Understandingcited by 8
  28. 2024Adversarial Text Purification: A Large Language Model Approach for Defensecited by 8
  29. 2022Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translationcited by 7
  30. 2022Mu2SLAM: Multitask, Multilingual Speech and Language Modelscited by 7
  31. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  32. 2021R&R: Metric-guided Adversarial Sentence Generationcited by 6
  33. 2021Addressing the Vulnerability of NMT in Input Perturbationscited by 6
  34. 2021Adversarial Training with Contrastive Learning in NLPcited by 6
  35. 2022Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modelingcited by 6
  36. 2021Targeted Adversarial Training for Natural Language Understandingcited by 5
  37. 2021Data Augmentation for Text Generation Without Any Augmented Datacited by 4
  38. 2021How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understandingcited by 4

50 most cited of 105 All 105 (JSON)