Symbolic Execution for Attribution and Attack Synthesis in Neural Networks

Abstract

This paper introduces DeepCheck, a new approach for validating Deep Neural Networks (DNNs) based on core ideas from program analysis, specifically from symbolic execution. DeepCheck implements techniques for lightweight symbolic analysis of DNNs and applies them in the context of image classification to address two challenging problems: 1) identification of important pixels (for attribution and adversarial generation); and 2) creation of adversarial attacks. Experimental results using the MNIST data-set show that DeepCheck's lightweight symbolic analysis provides a valuable tool for DNN validation.