# On Norm-Agnostic Robustness of Adversarial Training

arXiv: https://arxiv.org/abs/1905.06455 · HTML: https://mlsanity.com/paper/1905.06455/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2019.

## Built on by (most cited first, 1 of 1)

- [Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition](https://mlsanity.com/paper/2509.08225/) (2025)

## Abstract (arXiv)

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to increase robustness. In this paper, we propose a new attack to unveil an undesired property of the state-of-the-art adversarial training, that is it fails to obtain robustness against perturbations in ℓ2 and ℓ_∞ norms simultaneously. We discuss a possible solution to this issue and its limitations as well.