# Defending Against Image Corruptions Through Adversarial Augmentations

Source: [Defending Against Image Corruptions Through Adversarial Augmentations](<https://www.sota2.com/research/paper/68fa6b811e209131cea2eaf2>)

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

Data updated: 2025-10-25T23:50:06.694Z

Authors: Dan A. Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, Andras Gyorgy, Timothy Mann, Sven Gowal

Published: 2021-04-02T15:16:39.000Z

## Abstract

Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog. Recent methods that focus on this problem, such as AugMix and DeepAugment, introduce defenses that operate in expectation over a distribution of image corruptions. In contrast, the literature on $\\ell\_p$-norm bounded perturbations focuses on defenses against worst-case corruptions. In this work, we reconcile both approaches by proposing AdversarialAugment, a technique which optimizes the parameters of image-to-image models to generate adversarially corrupted augmented images. We theoretically motivate our method and give sufficient conditions for the consistency of its idealized version as well as that of DeepAugment. Our classifiers improve upon the state-of-the-art on common image corruption benchmarks conducted in expectation on CIFAR-10-C and improve worst-case performance against $\\ell\_p$-norm bounded perturbations on both CIFAR-10 and ImageNet.

## 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/2104.01086>)

[PDF](<https://arxiv.org/pdf/2104.01086.pdf>)