- Keywords: adversarial robustness, universal approximation, certified network, interval bound propagation
- TL;DR: We prove that for a large class of functions f there exists an interval certified robust network approximating f up to arbitrary precision.
- Abstract: Training neural networks to be certifiably robust is a powerful defense against adversarial attacks. However, while promising, state-of-the-art results with certified training are far from satisfactory. Currently, it is very difficult to train a neural network that is both accurate and certified on realistic datasets and specifications (e.g., robustness). Given this difficulty, a pressing existential question is: given a dataset and a specification, is there a network that is both certified and accurate with respect to these? While the evidence suggests "no", we prove that for realistic datasets and specifications, such a network does exist and its certification can be established by propagating lower and upper bounds of each neuron through the network (interval analysis) -- the most relaxed yet computationally efficient convex relaxation. Our result can be seen as a Universal Approximation Theorem for interval-certified ReLU networks. To the best of our knowledge, this is the first work to prove the existence of accurate, interval-certified networks.