Skip to yearly menu bar Skip to main content


Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

Jie Ren · Die Zhang · Yisen Wang · Lu Chen · Zhanpeng Zhou · Yiting Chen · Xu Cheng · Xin Wang · Meng Zhou · Jie Shi · Quanshi Zhang


Keywords: [ Robustness ] [ Deep Learning ] [ Adversarial Robustness and Security ]


This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial attacks mainly affect high-order interactions to fool the DNN. Furthermore, we find that the robustness of adversarially trained DNNs comes from category-specific low-order interactions. Our findings provide a potential method to unify adversarial perturbations and robustness, which can explain the existing robustness-boosting methods in a principle way. Besides, our findings also make a revision of previous inaccurate understanding of the shape bias of adversarially learned features. Our code is available online at

Chat is not available.