mlsanityData to 14 Oct 2026

Targeted Adversarial Attacks against Neural Machine Translation

arXiv 2303.01068 ↗First posted 2 Mar 2023cs.CL cs.CR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new targeted adversarial attack against NMT models. In particular, our goal is to insert a predefined target keyword into the translation of the adversarial sentence while maintaining similarity between the original sentence and the perturbed one in the source domain. To this aim, we propose an optimization problem, including an adversarial loss term and a similarity term. We use gradient projection in the embedding space to craft an adversarial sentence. Experimental results show that our attack outperforms Seq2Sick, the other targeted adversarial attack against NMT models, in terms of success rate and decrease in translation quality. Our attack succeeds in inserting a keyword into the translation for more than 75% of sentences while similarity with the original sentence stays preserved.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 19 of its 21 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

19 of 21 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 438
  8. 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 306
  9. 2018Marian: Fast Neural Machine Translation in C++cited by 203
  10. 2019Multilingual Universal Sentence Encoder for Semantic Retrievalcited by 193
  11. 2019Robust Neural Machine Translation with Doubly Adversarial Inputscited by 106
  12. 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 94
7 more
  1. 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
  2. 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 81
  3. 2020AdvAug: Robust Adversarial Augmentation for Neural Machine Translationcited by 67
  4. 2019On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Modelscited by 56
  5. 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
  6. 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
  7. 2022Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifierscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 1; 2026: 1.

10 papers.

  1. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  2. 2023A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translationcited by 4
  3. 2024Revisiting Character-level Adversarial Attacks for Language Modelscited by 4
  4. 2023Translate your gibberish: black-box adversarial attack on machine translation systemscited by 2
  5. 2024Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translationcited by 1
  6. 2023Machine Translation Models Stand Strong in the Face of Adversarial Attackscited by 0
  7. 2024BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memescited by 0
  8. 2024Rethinking Targeted Adversarial Attacks For Neural Machine Translationcited by 0
  9. 2024NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordcited by 0
  10. 2026When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasoundcited by 0