Concolic Testing for Deep Neural Networks

Concolic testing combines program execution and symbolic analysis to
explore the execution paths of a software program. We present the first
concolic testing approach for Deep Neural Networks (DNNs). More
specifically, we formalise coverage criteria for DNNs that have been
studied in the literature, and then develop a coherent method for
performing concolic testing to increase test coverage. Our experimental
results show the effectiveness of the concolic testing approach in both
achieving high coverage and finding adversarial examples.