Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

Abstract

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial examples created with large and less realistic distortions that are easily identified by human observers. In this paper, we propose a novel approach, called Adversarial Camouflage (AdvCam), to craft and camouflage physicalworld adversarial examples into natural styles that appear legitimate to human observers. Specifically, AdvCam transfers large adversarial perturbations into customized styles, which are then "hidden"on-target object or off-target background. ..