Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy [article]

Ruikui Wang, Yuanfang Guo, Ruijie Yang, Yunhong Wang
2021 arXiv   pre-print
The transferability and robustness of adversarial examples are two practical yet important properties for black-box adversarial attacks. In this paper, we explore effective mechanisms to boost both of them from the perspective of network hierarchy, where a typical network can be hierarchically divided into output stage, intermediate stage and input stage. Since over-specialization of source model, we can hardly improve the transferability and robustness of the adversarial perturbations in the
more » ... tput stage. Therefore, we focus on the intermediate and input stages in this paper and propose a transferable and robust adversarial perturbation generation (TRAP) method. Specifically, we propose the dynamically guided mechanism to continuously calculate accurate directional guidances for perturbation generation in the intermediate stage. In the input stage, instead of the single-form transformation augmentations adopted in the existing methods, we leverage multiform affine transformation augmentations to further enrich the input diversity and boost the robustness and transferability of the adversarial perturbations. Extensive experiments demonstrate that our TRAP achieves impressive transferability and high robustness against certain interferences.
arXiv:2108.07033v1 fatcat:d4okvsdl45gq5kp5wto3yvfaiq