Competition on robust deep learning

Authors: Yinpeng Dong, Chang Liu, Wenzhao Xiang, Hang Su, Jun Zhu

Published: 2023-04-08

DOI: 10.1093/nsr/nwad087

Source: Full article


Abstract

This perspective paper proposes a new adversarial training method based on large-scale pre-trained models to achieve state-of-the-art adversarial robustness on ImageNet.