Artificial neural networks are prone to being fooled by carefully perturbed inputs which cause an egregious misclassification. These \textit{adversarial} attacks have been the focus of extensive research. Likewise, there has been an abundance of research in ways to detect and defend against them. We introduce a novel approach of detection and interpretation of adversarial attacks from a graph perspective. For an image, benign or adversarial, we study how a neural network's architecture can induce an associated graph. We study this graph and introduce specific measures used to predict and interpret adversarial attacks. We show that graphs-based approaches help to investigate the inner workings of adversarial attacks.

翻译：暂无翻译