LGCRMLJan 8, 2020

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

arXiv:2001.02378v4199 citations
Originality Highly original
AI Analysis

This addresses the need for scalable and efficient robust training in machine learning, offering a novel approach that avoids adversarial attacks, though it builds on existing randomized smoothing techniques.

The paper tackles the problem of adversarial training being attack-dependent and computationally expensive by proposing MACER, an attack-free algorithm that trains provably robust smoothed classifiers via maximizing certified radius, achieving larger average certified radius and faster training times than state-of-the-art adversarial training methods on datasets like Cifar-10 and ImageNet.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes