RobustAugMix: Joint Optimization of Natural and Adversarial RobustnessDownload PDF

Published: 05 Dec 2022, Last Modified: 05 May 2023MLSW2022Readers: Everyone
Abstract: Machine learning models often suffer performance degradation when faced with corrupted data. In this work, we explore a technique that combines a data augmentation strategy (AugMix) with adversarial training, in order to increase robustness to both natural and adversarial forms of data corruption.
1 Reply