A new method of detecting adversarial attacks is proposed for an ensemble of Deep Neural Networks (DNNs) solving two-class pattern recognition problems. The ensemble is combined using Walsh coefficients which are capable of approximating Boolean functions and thereby controlling the complexity of the ensemble decision boundary. The hypothesis in this paper is that decision boundaries with high curvature allow adversarial perturbations to be found, but change the curvature of the decision boundary, which is then approximated in a different way by Walsh coefficients compared to the clean images. By observing the difference in Walsh coefficient approximation between clean and adversarial images, it is shown experimentally that transferability of attack may be used for detection. Furthermore, approximating the decision boundary may aid in understanding the learning and transferability properties of DNNs. While the experiments here use images, the proposed approach of modelling two-class ensemble decision boundaries could in principle be applied to any application area. Code for approximating Boolean functions using Walsh coefficients: https://doi.org/10.24433/CO.3695905.v1
翻译:暂无翻译