Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversarial training but performs better than all existing provable l2-defenses. Recent work shows that randomized smoothing can be used to provide a certified l2 radius to smoothed classifiers, and our algorithm trains provably robust smoothed classifiers via MAximizing the CErtified Radius (MACER). The attack-free characteristic makes MACER faster to train and easier to optimize. In our experiments, we show that our method can be applied to modern deep neural networks on a wide range of datasets, including Cifar-10, ImageNet, MNIST, and SVHN. For all tasks, MACER spends less training time than state-of-the-art adversarial training algorithms, and the learned models achieve larger average certified radius.
@article{arxiv.2001.02378,
title = {MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius},
author = {Runtian Zhai and Chen Dan and Di He and Huan Zhang and Boqing Gong and Pradeep Ravikumar and Cho-Jui Hsieh and Liwei Wang},
journal= {arXiv preprint arXiv:2001.02378},
year = {2022}
}