Perturbations on the Perceptual Ball.

We present a simple regularisation of Adversarial Perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in two important regards: (i) our resulting perturbations are semi-sparse, and typically make alterations to objects and regions of interest leaving the background static; (ii) our perturbations do not alter the distribution of data in the image and are undetectable by state-of-the-art methods. As such this work reinforces the connection between explainable AI and adversarial perturbations. We demonstrate the merits of our approach by evaluating on standard explainability benchmark and by defeating a recent test for detecting adversarial perturbations.