Translate your gibberish: black-box adversarial attack on machine translation systems
Not on the map. Why?
Abstract (arXiv)
Neural networks are deployed widely in natural language processing tasks on the industrial scale, and perhaps the most often they are used as compounds of automatic machine translation systems. In this work, we present a simple approach to fool state-of-the-art machine translation tools in the task of translation from Russian to English and vice versa. Using a novel black-box gradient-free tensor-based optimizer, we show that many online translation tools, such as Google, DeepL, and Yandex, may both produce wrong or offensive translations for nonsensical adversarial input queries and refuse to translate seemingly benign input phrases. This vulnerability may interfere with understanding a new language and simply worsen the user's experience while using machine translation systems, and, hence, additional improvements of these tools are required to establish better translation.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 20 Mar 2023.
Builds on
23 of 31 references.
References · 23
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Intriguing properties of neural networkscited by 5,114
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
- 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
- 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
- 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
- 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
- 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
- 2018Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examplescited by 93
11 more
- 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
- 2022Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translationcited by 60
- 2017Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectivescited by 53
- 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
- 2018Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehensioncited by 19
- 2022TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learningcited by 15
- 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
- 2023Targeted Adversarial Attacks against Neural Machine Translationcited by 10
- 2022Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifierscited by 9
- 2022Optimization of Functions Given in the Tensor Train Formatcited by 7
- 2022PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translationcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.