$\ddot{I}ƒ$-zero: Gradient-based Optimization of ${\ell }_0$-norm Adversarial Examples

Antonio Emanuele CinÃ, Francesco Villani, Maura Pintor +3

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider ${\ell }_2$- and ${\ell }_{\infty }$-norm constraints to craft i…