Symbolic Execution for Importance Analysis and Adversarial Generation in Neural Networks

Deep Neural Networks (DNN) are increasingly used in a variety of applications, many of them with serious safety and security concerns. This paper describes DeepCheck, a new approach for validating DNNs based on core ideas from program analysis, specifically from symbolic execution. DeepCheck implements novel techniques for lightweight symbolic analysis of DNNs and applies them to address two challenging problems in DNN analysis: 1) identification of important input features and 2) leveraging those features to create adversarial inputs. Experimental results with an MNIST image classification network and a sentiment network for textual data show that DeepCheck promises to be a valuable tool for DNN analysis.