Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples according to the underlying data distribution, which is apparently unrealistic as the attacker could choose to focus on more vulnerable examples. We present a weighted minimax risk optimization that defends against non-uniform attacks, achieving robustness against adversarial examples under perturbed test data distributions. Our modified risk considers importance weights of different adversarial examples and focuses adaptively on harder examples that are wrongly classified or at higher risk of being classified incorrectly. The designed risk allows the training process to learn a strong defense through optimizing the importance weights. The experiments show that our model significantly improves state-of-the-art adversarial accuracy under non-uniform attacks without a significant drop under uniform attacks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Entropy Weighted Adversarial Training
Adversarial training methods, which minimizes the loss of adversarially-perturbed training examples, have been extensively studied as a solution to improve the robustness of the deep neural networks. However, most advers…
Detection and Defense of Unlearnable Examples
Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Internet by degrading generalization abilities …
Adversarial DefensePrivacy PreservingImproving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Adversarial training (AT) trains models using adversarial examples (AEs), which are natural images modified with specific perturbations to mislead the model. These perturbations are constrained by a predefined perturbati…
Robust classificationRobust Unlearnable Examples: Protecting Data Against Adversarial Learning
The tremendous amount of accessible data in cyberspace face the risk of being unauthorized used for training deep learning models. To address this concern, methods are proposed to make data unlearnable for deep learning …
Full spectrum Unlearnable Examples via Spectral Equalization
Unlearnable examples (UEs) protect training data by injecting imperceptible perturbations so that models fail to extract exploitable representations. In this paper, we reveal that existing UEs exhibit a critical failure …