# Machine Translation Models Stand Strong in the Face of Adversarial Attacks

arXiv: https://arxiv.org/abs/2309.06527 · HTML: https://mlsanity.com/paper/2309.06527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [Robust Neural Machine Translation with Doubly Adversarial Inputs](https://mlsanity.com/paper/1906.02443/) (2019)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [On Adversarial Examples for Character-Level Neural Machine Translation](https://mlsanity.com/paper/1806.09030/) (2018)
- [Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification](https://mlsanity.com/paper/1909.03084/) (2019)
- [On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models](https://mlsanity.com/paper/1903.06620/) (2019)
- [Towards Crafting Text Adversarial Samples](https://mlsanity.com/paper/1707.02812/) (2017)
- [Improving Robustness of Machine Translation with Synthetic Noise](https://mlsanity.com/paper/1902.09508/) (2019)
- [Targeted Adversarial Attacks against Neural Machine Translation](https://mlsanity.com/paper/2303.01068/) (2023)
- [A Differentiable Language Model Adversarial Attack on Text Classifiers](https://mlsanity.com/paper/2107.11275/) (2021)
- [Towards a Robust Deep Neural Network in Texts: A Survey](https://mlsanity.com/paper/1902.07285/) (2019)
- [Differentiable lower bound for expected BLEU score](https://mlsanity.com/paper/1712.04708/) (2017)
- [Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world](https://mlsanity.com/paper/2003.04173/) (2020)

## Abstract (arXiv)

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on sequence-to-sequence (seq2seq) models, specifically machine translation models. We introduce algorithms that incorporate basic text perturbation heuristics and more advanced strategies, such as the gradient-based attack, which utilizes a differentiable approximation of the inherently non-differentiable translation metric. Through our investigation, we provide evidence that machine translation models display robustness displayed robustness against best performed known adversarial attacks, as the degree of perturbation in the output is directly proportional to the perturbation in the input. However, among underdogs, our attacks outperform alternatives, providing the best relative performance. Another strong candidate is an attack based on mixing of individual characters.