A New Kind of Adversarial Example. (arXiv:2208.02430v1 [cs.CV])

Almost all adversarial attacks are formulated to add an imperceptible
perturbation to an image in order to fool a model. Here, we consider the
opposite which is adversarial examples that can fool a human but not a model. A
large enough and perceptible perturbation is added to an image such that a
model maintains its original decision, whereas a human will most likely make a
mistake if forced to decide (or opt not to decide at all). Existing targeted
attacks …

arxiv cv example kind