SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation

Wuxinlin Cheng, Chenhui Deng, Zhiqiang Zhao, Yaohui Cai, Zhiru Zhang, Zhuo Feng

Abstract: A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance mapping between th...