Fig. 4From: Deep neural rejection against adversarial examplesInfluence of the rejection threshold ? on classifier accuracy under attack (y-axis) vs false rejection rate (i.e., fraction of wrongly rejected unperturbed samples) on MNIST (top) and CIFAR10 (bottom) for NR (left) and DNR (right), for different ?-sized attacks. The dashed line highlights the performance at 10% false rejection rate (i.e., the operating point used in our experiments)Back to article page