Expressive Losses for Verified Robustness via Convex Combinations

arXiv:2305.13991v2 Announce Type: replace
Abstract: In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance. As shown in recent work, better trade-offs between accuracy and robustness can be obtained by carefully coupling adversarial training with over-approximations. We hypothesize that the expressivity of a loss function, which we formalize as the ability to span a range of trade-offs between …

abstract accuracy adversarial arxiv case cs.cr cs.lg loss losses networks performance robustness standard stat.ml trade train type via work