Timezone: »

 
Poster
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

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ Virtual
in Poster Session 3 »

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 https://github.com/Jie-Ren/A-Unified-Game-Theoretic-Interpretation-of-Adversarial-Robustness.

Keywords: Deep Learning · Robustness · Adversarial Robustness and Security

Author Information

Jie Ren (Shanghai Jiao Tong University)
Die Zhang (Shanghai Jiaotong University)
Yisen Wang (Peking University)
Lu Chen (, Shanghai Jiao Tong University)
Zhanpeng Zhou (Shanghai Jiao Tong University)
Yiting Chen (Shanghai Jiao Tong University)
Xu Cheng (Shanghai Jiao Tong University)
Xin Wang (Shanghai Jiao Tong University)
Meng Zhou (Shanghai Jiao Tong University)
Jie Shi (Huawei International.)
Quanshi Zhang (University of Tokyo)

More from the Same Authors