# On the effectiveness of adversarial training against common corruptions

Source: [On the effectiveness of adversarial training against common corruptions](<https://www.sota2.com/research/paper/68fa6b891e209131cea2ef50>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:51:06.318Z

Authors: Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion

Published: 2021-03-03T11:04:09.000Z

## Abstract

The literature on robustness towards common corruptions shows no consensus on whether adversarial training can improve the performance in this setting. First, we show that, when used with an appropriately selected perturbation radius, $\\ell\_p$ adversarial training can serve as a strong baseline against common corruptions improving both accuracy and calibration. Then we explain why adversarial training performs better than data augmentation with simple Gaussian noise which has been observed to be a meaningful baseline on common corruptions. Related to this, we identify the $\\sigma$-overfitting phenomenon when Gaussian augmentation overfits to a particular standard deviation used for training which has a significant detrimental effect on common corruption accuracy. We discuss how to alleviate this problem and then how to further enhance $\\ell\_p$ adversarial training by introducing an efficient relaxation of adversarial training with learned perceptual image patch similarity as the distance metric. Through experiments on CIFAR-10 and ImageNet-100, we show that our approach does not only improve the $\\ell\_p$ adversarial training baseline but also has cumulative gains with data augmentation methods such as AugMix, DeepAugment, ANT, and SIN, leading to state-of-the-art performance on common corruptions.   The code of our experiments is publicly available at https://github.com/tml-epfl/adv-training-corruptions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.02325>)

[PDF](<https://arxiv.org/pdf/2103.02325.pdf>)
