Input Validation for Neural Networks via Runtime Local Robustness Verification

Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adversarial examples, especially those from strong adversarial attacks. Another observation is that the robustness radii of correctly classified inputs often follow a normal distribution. Based on these two observations, we propose to …

adversarial adversarial examples call cs.lg examples inputs network networks neural network neural networks observe robust robustness stat.ml validation verification verify via