An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks
This work addresses the problem of evaluating adversarial robustness in deep learning for researchers and practitioners, though it is incremental as it builds on existing methods with a focus on explainability.
The authors tackled the lack of an explainable adversarial robustness metric for deep neural networks by proposing the Noise Sensitivity Score (NSS), which quantifies performance under fix-directional attacks and includes a skewness-based dataset metric, validated on datasets like MNIST, CIFAR-10, CIFAR-100, and ImageNet with state-of-the-art architectures.
Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these adversarial inputs is still missing from the literature. In this paper, we propose Noise Sensitivity Score (NSS), a metric that quantifies the performance of a DNN on a specific input under different forms of fix-directional attacks. An insightful mathematical explanation is provided for deeply understanding the proposed metric. By leveraging the NSS, we also proposed a skewness based dataset robustness metric for evaluating a DNN's adversarial performance on a given dataset. Extensive experiments using widely used state of the art architectures along with popular classification datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet, are used to validate the effectiveness and generalization of our proposed metrics. Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.