Verification and Repair of Neural Networks: A Progress Report on Convolutional Models

Recent public calls for the development of explainable and verifiable AI led to a growing interest in formal verification and repair of machine-learned models. Despite the impressive progress that the learning community has made, models such as deep neural networks remain vulnerable to adversarial attacks, and their sheer size represents a major obstacle to formal analysis and implementation. In this paper we present our current efforts to tackle repair of deep convolutional neural networks using ideas borrowed from Transfer Learning. With results obtained on popular MNIST and CIFAR10 datasets, we show that models of deep convolutional neural networks can be transformed into simpler ones preserving their accuracy, and we discuss how formal repair through convex programming techniques could benefit from this process