# Adversarially Robust Training through Structured Gradient Regularization

arXiv: https://arxiv.org/abs/1805.08736 · HTML: https://mlsanity.com/paper/1805.08736/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 5 of 5)

- [The Geometry of Adversarial Training in Binary Classification](https://mlsanity.com/paper/2111.13613/) (2021)
- [On the regularized risk of distributionally robust learning over deep neural networks](https://mlsanity.com/paper/2109.06294/) (2021)
- [Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis](https://mlsanity.com/paper/2103.00778/) (2021)
- [On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce it](https://mlsanity.com/paper/2301.03662/) (2023)
- [Identifying and Exploiting Structures for Reliable Deep Learning](https://mlsanity.com/paper/2108.07083/) (2021)

## Abstract (arXiv)

We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived as a controlled approximation from first principles, leveraging the fundamental link between training with noise and regularization. It adds very little computational overhead during learning and is simple to implement generically in standard deep learning frameworks. Our experiments provide strong evidence that structured gradient regularization can act as an effective first line of defense against attacks based on low-level signal corruption.