Feature prioritization and regularization improve standard accuracy and adversarial robustness
Adversarial training has been successfully applied to build robust models at a certain cost. While the robustness of a model increases, the standard classification accuracy declines. This phenomenon is suggested to be an inherent trade-off between standard accuracy and robustness. We propose a model that employs feature prioritization by a nonlinear attention module and L_2 regularization as implicit denoising to improve the adversarial robustness and the standard accuracy relative to adversarial training. Focusing sharply on the regions of interest, the attention maps encourage the model to rely heavily on features extracted from the most relevant areas while suppressing the unrelated background. Penalized by a regularizer, the model extracts similar features for the natural and adversarial images, effectively ignoring the added perturbation. In addition to qualitative evaluation, we also propose a novel experimental strategy that quantitatively demonstrates that our model is almost ideally aligned with salient data characteristics. Additional experimental results illustrate the power of our model relative to the state of the art methods.
READ FULL TEXT