Provable Robustness of Adversarial Training for Learning Halfspaces with Noise (2104.09437v1)

Abstract: We analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}{p,r}$ as the best robust classification error achieved by a halfspace that is robust to perturbations of $\ell{p}$ balls of radius $r$, we show that adversarial training on the standard binary cross-entropy loss yields adversarially robust halfspaces up to (robust) classification error $\tilde O(\sqrt{\mathsf{OPT}{2,r}})$ for $p=2$, and $\tilde O(d^{1/4} \sqrt{\mathsf{OPT}{\infty, r}} + d^{1/2} \mathsf{OPT}{\infty,r})$ when $p=\infty$. Our results hold for distributions satisfying anti-concentration properties enjoyed by log-concave isotropic distributions among others. We additionally show that if one instead uses a nonconvex sigmoidal loss, adversarial training yields halfspaces with an improved robust classification error of $O(\mathsf{OPT}{2,r})$ for $p=2$, and $O(d^{1/4}\mathsf{OPT}_{\infty, r})$ when $p=\infty$. To the best of our knowledge, this is the first work to show that adversarial training provably yields robust classifiers in the presence of noise.