How explainable are adversarially-robust CNNs?

no code implementations • 25 May 2022 • Mehdi Nourelahi, Lars Kotthoff, Peijie Chen, Anh Nguyen

Here, we perform the first, large-scale evaluation of the relations of the three criteria using 9 feature-importance methods and 12 ImageNet-trained CNNs that are of 3 training algorithms and 5 CNN architectures.

Feature Importance