Provable Adversarial Robustness for Fractional Lp Threat Models
Alexander Levine, Soheil Feizi · arXiv (Cornell University) · 2022
In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms" (quasi-norms defined by the L_p distance with 0