Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples.

ABSTRACT: Adversarial attacks are still a significant challenge for neural networks. Recent efforts have shown that adversarial perturbations typically contain high-frequency features, but the root cause of this phenomenon remains unknown. Inspired by theoretical work on linear convolutional models, we hypothesize that translational symmetry in convolutional operations together with localized kernels implicitly bias the learning of high-frequency features, and that this is one of the main causes of high frequency adversarial examples. To test this hypothesis, we analyzed the impact of different choices of linear and non-linear architectures on the implicit bias of the learned features and adversarial perturbations, in spatial and frequency domains. We find that, independe

SUBMITTER: Caro JO 

PROVIDER: S-EPMC11222393 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature