Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts

Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer +1

Adversarial training is widely used to make classifiers robust to a specific threat or adversary, such as ${\ell }_p$-norm bounded perturbations of a given $p$-norm. However, existing…