Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Machine Learning Safety

RobustAugMix: Joint Optimization of Natural and Adversarial Robustness

Josue Martinez-Martinez · Olivia Brown


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.

Chat is not available.