TAPS: Connecting Certified and Adversarial Training

Autor:	Mao, Yuhao, Müller, Mark Niklas, Fischer, Marc, Vechev, Martin
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Training certifiably robust neural networks remains a notoriously hard problem. On one side, adversarial training optimizes under-approximations of the worst-case loss, which leads to insufficient regularization for certification, while on the other, sound certified training methods optimize loose over-approximations, leading to over-regularization and poor (standard) accuracy. In this work we propose TAPS, an (unsound) certified training method that combines IBP and PGD training to yield precise, although not necessarily sound, worst-case loss approximations, reducing over-regularization and increasing certified and standard accuracies. Empirically, TAPS achieves a new state-of-the-art in many settings, e.g., reaching a certified accuracy of $22\%$ on TinyImageNet for $\ell_\infty$-perturbations with radius $\epsilon=1/255$. We make our implementation and networks public at https://github.com/eth-sri/taps. Comment: NeuIPS'23
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.04574 Zobrazit plný text záznamu View this record from Arxiv