# Extend Adversarial Policy Against Neural Machine Translation via Unknown Token

arXiv: https://arxiv.org/abs/2501.12183 · HTML: https://mlsanity.com/paper/2501.12183/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 21 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Robust Neural Machine Translation with Doubly Adversarial Inputs](https://mlsanity.com/paper/1906.02443/) (2019)
- [Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples](https://mlsanity.com/paper/1803.01128/) (2018)
- [Learning Compact Metrics for MT](https://mlsanity.com/paper/2110.06341/) (2021)
- [On Adversarial Examples for Character-Level Neural Machine Translation](https://mlsanity.com/paper/1806.09030/) (2018)
- [Reevaluating Adversarial Examples in Natural Language](https://mlsanity.com/paper/2004.14174/) (2020)
- [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)
- [Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation](https://mlsanity.com/paper/1902.01509/) (2019)
- [SemAttack: Natural Textual Attacks via Different Semantic Spaces](https://mlsanity.com/paper/2205.01287/) (2022)
- [Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers](https://mlsanity.com/paper/2203.05948/) (2022)
- [Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation](https://mlsanity.com/paper/2305.14189/) (2023)
- [Exploring the Robustness of NMT Systems to Nonsensical Inputs](https://mlsanity.com/paper/1908.01165/) (2019)
- [On Adversarial Examples for Text Classification by Perturbing Latent Representations](https://mlsanity.com/paper/2405.03789/) (2024)

## Abstract (arXiv)

Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness. However, popular adversarial policies are apt for fixed tokenization, hindering its efficacy for common character perturbations involving versatile tokenization. Based on existing adversarial generation via reinforcement learning~(RL), we propose the `DexChar policy' that introduces character perturbations for the existing mainstream adversarial policy based on token substitution. Furthermore, we improve the self-supervised matching that provides feedback in RL to cater to the semantic constraints required during training adversaries. Experiments show that our method is compatible with the scenario where baseline adversaries fail, and can generate high-efficiency adversarial examples for analysis and optimization of the system.