We propose the novel certified training method, SABR, which outperforms existing methods across perturbation magnitudes on MNIST, CIFAR-10, and TinyImageNet, in terms of both standard and certifiable accuracies. The key insight behind SABR is 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. SABR does not only establish a new state-of-the-art in all commonly used benchmarks but more importantly, points to a new class of certified training methods promising to overcome the robustness-accuracy trade-off.

@article{mueller2022certified, author = {Mark Niklas M{\"{u}}ller and Franziska Eckert and Marc Fischer and Martin T. Vechev}, title = {Certified Training: Small Boxes are All You Need}, journal = {CoRR}, year = {2022}, doi = {10.48550/arXiv.2210.04871}, }