Concolic Testing for Deep Neural Networks
This addresses the need for robust testing methods in deep learning systems, though it is incremental as it adapts existing concolic testing to a new domain.
The paper tackled the problem of testing deep neural networks by introducing the first concolic testing approach, which formalizes coverage criteria and increases test coverage, with experimental results showing effectiveness in achieving high coverage and finding adversarial examples.
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents 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.