A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{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 defense methods in a principle way. Besides, our findings also make a revision of previous inaccurate understanding of the shape bias of adversarially learned features.
Code (1)
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
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 discove…
Adversarial RobustnessA Unified Game-Theoretic Interpretation of Adversarial Robustness
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 discove…
Adversarial RobustnessNash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
Adversarial training is a standard technique for training adversarially robust models. In this paper, we study adversarial training as an alternating best-response strategy in a 2-player zero-sum game. We prove that even…
Adversarial RobustnessVisual Interpretability Alone Helps Adversarial Robustness
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks. In this paper, we t…
Adversarial RobustnessGame Theoretic Mixed Experts for Combinational Adversarial Machine Learning
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defense…
Adversarial Defense