Recent works have shown that it is possible to train models that are verifiably robust to norm-bounded adversarial perturbations. While these recent methods show promise, they remain hard to scale and difficult to tune. This paper investigates how interval bound propagation (IBP) using simple interval arithmetic can be exploited to train verifiably robust neural networks that are surprisingly effective. While IBP itself has been studied in prior work, our contribution is in showing that, with an appropriate loss and careful tuning of hyper-parameters, verified training with IBP leads to a fast and stable learning algorithm. We compare our approach with recent techniques, and train classifiers that improve on the state-of-the-art in single-model adversarial robustness: we reduce the verified error rate from 3.67% to 2.23% on M

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that the outputs of the neural network will always behave in a certain way for a given class of inputs. Most previous work on this topic was limited in its applicability by the size of the network, network architecture and the complexity of properties to be verified. In contrast, our framework applies to much more general class of activation functions and specifications on neural network inputs and outputs. We formulate verification as an optimization problem and solve a Lagrangian relaxation of the optimization problem to obtain an upper bound on the verification objective. Our approach is anytime, i.e. it can be stopped at any time and a valid bound on the objective can be obtained. We develop specialized verification algorithms with provable tightness guarantees under special assumptions and demonstrate the practical significance of our general verification approach on a variety of verification tasks.