# Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training

arXiv: https://arxiv.org/abs/2009.12064 · HTML: https://mlsanity.com/paper/2009.12064/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Improved Text Classification via Contrastive Adversarial Training](https://mlsanity.com/paper/2107.10137/) (2021)
- [SEAT: Stable and Explainable Attention](https://mlsanity.com/paper/2211.13290/) (2022)
- [SATO: Stable Text-to-Motion Framework](https://mlsanity.com/paper/2405.01461/) (2024)
- [Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training](https://mlsanity.com/paper/2104.08763/) (2021)
- [On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations](https://mlsanity.com/paper/2201.00318/) (2022)
- [A Novel Approach to Train Diverse Types of Language Models for Health Mention Classification of Tweets](https://mlsanity.com/paper/2204.06337/) (2022)
- [Proactive Schemes: A Survey of Adversarial Attacks for Social Good](https://mlsanity.com/paper/2409.16491/) (2024)
- [Improving Health Mentioning Classification of Tweets using Contrastive Adversarial Training](https://mlsanity.com/paper/2203.01895/) (2022)
- [COmic: Convolutional Kernel Networks for Interpretable End-to-End Learning on (Multi-)Omics Data](https://mlsanity.com/paper/2212.02504/) (2022)
- [Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives](https://mlsanity.com/paper/2303.14116/) (2023)
- [How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair](https://mlsanity.com/paper/2607.25873/) (2026)
- [Prescriptive SVD-Inspired Attention via Spectral Energy Retention](https://mlsanity.com/paper/2609.24370/) (2026)

## Abstract (arXiv)

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the vulnerability to perturbations in the mechanism, we are inspired by adversarial training (AT), which is a powerful regularization technique for enhancing the robustness of the models. In this paper, we propose a general training technique for natural language processing tasks, including AT for attention (Attention AT) and more interpretable AT for attention (Attention iAT). The proposed techniques improved the prediction performance and the model interpretability by exploiting the mechanisms with AT. In particular, Attention iAT boosts those advantages by introducing adversarial perturbation, which enhances the difference in the attention of the sentences. Evaluation experiments with ten open datasets revealed that AT for attention mechanisms, especially Attention iAT, demonstrated (1) the best performance in nine out of ten tasks and (2) more interpretable attention (i.e., the resulting attention correlated more strongly with gradient-based word importance) for all tasks. Additionally, the proposed techniques are (3) much less dependent on perturbation size in AT. Our code is available at https://github.com/shunk031/attention-meets-perturbation