# A Reinforced Generation of Adversarial Examples for Neural Machine Translation

arXiv: https://arxiv.org/abs/1911.03677 · HTML: https://mlsanity.com/paper/1911.03677/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 9 of 9)

- [Bad Characters: Imperceptible NLP Attacks](https://mlsanity.com/paper/2106.09898/) (2021)
- [Boosting Fast Adversarial Training with Learnable Adversarial Initialization](https://mlsanity.com/paper/2110.05007/) (2021)
- [Prior-Guided Adversarial Initialization for Fast Adversarial Training](https://mlsanity.com/paper/2207.08859/) (2022)
- [OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs](https://mlsanity.com/paper/2601.01592/) (2026)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2110.05691/) (2021)
- [Sentiment Perception Adversarial Attacks on Neural Machine Translation Systems](https://mlsanity.com/paper/2305.01437/) (2023)
- [Masked Adversarial Generation for Neural Machine Translation](https://mlsanity.com/paper/2109.00417/) (2021)

## Abstract (arXiv)

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical for industrial maintenance. Instead of collecting and analyzing bad cases using limited handcrafted error features, here we investigate this issue by generating adversarial examples via a new paradigm based on reinforcement learning. Our paradigm could expose pitfalls for a given performance metric, e.g., BLEU, and could target any given neural machine translation architecture. We conduct experiments of adversarial attacks on two mainstream neural machine translation architectures, RNN-search, and Transformer. The results show that our method efficiently produces stable attacks with meaning-preserving adversarial examples. We also present a qualitative and quantitative analysis for the preference pattern of the attack, demonstrating its capability of pitfall exposure.