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.
Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitzcontinuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the function are Lipschitz continuous, all values in the interval between the lower and upper bound are reachable. We show how to obtain the safety verification problem, the output range analysis problem and a robustness measure by instantiating the reachability problem. We present a novel algorithm based on adaptive nested optimisation to solve the reachability problem. The technique has been implemented and evaluated on a range of DNNs, demonstrating its efficiency, scalability and ability to handle a broader class of networks than state-of-the-art verification approaches.
Epidermal pH is an indication of the skin’s physiological condition. For example, pH of wound can be correlated to angiogenesis, protease activity, bacterial infection, etc. Chronic non-healing wounds are known to have an elevated alkaline environment, while healing process occurs more readily in an acidic environment. Thus, dermal patches capable of continuous monitoring of pH can be used as point-of-care systems for monitoring skin disorder and the wound healing process. Here, we present pH-responsive hydrogel fibers that can be used for long-term monitoring of epidermal wound condition. We load pH-responsive dyes into mesoporous microparticles and incorporate them into hydrogel fibers developed through microfluidic spinning. The fabricated pH-responsive microfibers are flexible and can create conformal contact with skin. The response of pH-sensitive fibers with different compositions and thicknesses are characterized. The suggested technique is scalable and can be used to fabricate hydrogel based wound dressing with a wide range of sizes. Images of the pH-sensing fibers during real-time pH measurement can be captured with a smart phone camera for convenient readout on-site. Through image processing, a quantitative pH map of the hydrogel fibers and the underlying tissue can be extracted. The developed skin dressing can act as a point-of-care device for monitoring the wound healing process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.