# Rethinking Targeted Adversarial Attacks For Neural Machine Translation

arXiv: https://arxiv.org/abs/2407.05319 · HTML: https://mlsanity.com/paper/2407.05319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Gradient-based Adversarial Attacks against Text Transformers](https://mlsanity.com/paper/2104.13733/) (2021)
- [Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples](https://mlsanity.com/paper/1803.01128/) (2018)
- [On Adversarial Examples for Character-Level Neural Machine Translation](https://mlsanity.com/paper/1806.09030/) (2018)
- [Imitation Attacks and Defenses for Black-box Machine Translation Systems](https://mlsanity.com/paper/2004.15015/) (2020)
- [On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models](https://mlsanity.com/paper/1903.06620/) (2019)
- [Targeted Adversarial Attacks against Neural Machine Translation](https://mlsanity.com/paper/2303.01068/) (2023)
- [Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation](https://mlsanity.com/paper/2204.08689/) (2022)

## Abstract (arXiv)

Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversarial attacks, where their attacking results are largely overestimated. To this end, this paper presents a new setting for NMT targeted adversarial attacks that could lead to reliable attacking results. Under the new setting, it then proposes a Targeted Word Gradient adversarial Attack (TWGA) method to craft adversarial examples. Experimental results demonstrate that our proposed setting could provide faithful attacking results for targeted adversarial attacks on NMT systems, and the proposed TWGA method can effectively attack such victim NMT systems. In-depth analyses on a large-scale dataset further illustrate some valuable findings. 1 Our code and data are available at https://github.com/wujunjie1998/TWGA.