Hanshu Yan

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

2021 · arXiv (Cornell University)

We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise …