The Effects of Image Distribution and Task on Adversarial Robustness

no code implementations • 21 Feb 2021 • Owen Kunhardt, Arturo Deza, Tomaso Poggio

In this paper, we propose an adaptation to the area under the curve (AUC) metric to measure the adversarial robustness of a model over a particular $\epsilon$-interval $[\epsilon_0, \epsilon_1]$ (interval of adversarial perturbation strengths) that facilitates unbiased comparisons across models when they have different initial $\epsilon_0$ performance.

Adversarial Robustness Object Recognition