Certified Training: Small Boxes are All You Need

Autor:	Müller, Mark Niklas, Eckert, Franziska, Fischer, Marc, Vechev, Martin
Rok vydání:	2022
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds for a small but carefully selected subset of the adversarial input region is sufficient to approximate the worst-case loss over the whole region while significantly reducing approximation errors. We show in an extensive empirical evaluation that SABR outperforms existing certified defenses in terms of both standard and certifiable accuracies across perturbation magnitudes and datasets, pointing to a new class of certified training methods promising to alleviate the robustness-accuracy trade-off. Comment: Accepted at ICLR23 as Spotlight
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2210.04871 Zobrazit plný text záznamu View this record from Arxiv