DeepAI AI Chat
Log In Sign Up

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

by   Runtian Zhai, et al.
Carnegie Mellon University
Peking University

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.


page 1

page 2

page 3

page 4


Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Recent works have shown the effectiveness of randomized smoothing as a s...

Simpler Certified Radius Maximization by Propagating Covariances

One strategy for adversarially training a robust model is to maximize it...

Do we need entire training data for adversarial training?

Deep Neural Networks (DNNs) are being used to solve a wide range of prob...

Provable Robust Classification via Learned Smoothed Densities

Smoothing classifiers and probability density functions with Gaussian ke...

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

We analyze the properties of adversarial training for learning adversari...

Input-Specific Robustness Certification for Randomized Smoothing

Although randomized smoothing has demonstrated high certified robustness...