Transfer of Adversarial Robustness Between Perturbation Types
This work addresses the need for more comprehensive evaluation of adversarial defenses for researchers and practitioners, though it is incremental as it builds on existing adversarial training methods.
The paper tackled the problem of whether adversarial robustness transfers between different perturbation types in deep neural networks, finding that robustness against one type may not imply or can even hurt robustness against others, based on evaluating 32 attacks across 5 types on a 100-class ImageNet subset.
We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on $L_\infty$ and $L_2$-bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attacks of 5 different types against models adversarially trained on a 100-class subset of ImageNet. Our empirical results suggest that evaluating on a wide range of perturbation sizes is necessary to understand whether adversarial robustness transfers between perturbation types. We further demonstrate that robustness against one perturbation type may not always imply and may sometimes hurt robustness against other perturbation types. In light of these results, we recommend evaluation of adversarial defenses take place on a diverse range of perturbation types and sizes.