Keywords: Neural Network Verification, Adversarial Robustness, Graph Neural Networks, Optimization
TL;DR: We improve existing Bounding Methods for Neural Network Verification Algorithms using Graph Neural Networks
Abstract: Recent years have witnessed the deployment of branch-and-bound (BaB) frameworks for formal verification in deep learning. The main computational bottleneck of BaB is the estimation of lower bounds. Past work in this field has relied on traditional optimization algorithms whose inefficiencies have limited their scope. To alleviate this deficiency, we propose a novel graph neural network (GNN) based approach. Our GNN architecture closely resembles the network we wish to verify. During inference, it performs forward-backward passes through the GNN layers to compute a dual solution of the convex relaxation, thereby providing a valid lower bound. During training, its parameters are estimated via a loss function that encourages large lower bounds over a time horizon. We show that our approach provides a significant speedup for formal verification compared to state-of-the-art solvers and achieves good generalization performance on unseen networks.