File(s) under permanent embargo
Adversarial camouflage: Hiding physical-world attacks with natural styles
conference contributionposted on 2020-01-01, 00:00 authored by R Duan, Daniel Ma, Y Wang, J Bailey, A K Qin, Y Yang
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, calledAdversarial Camouflage (AdvCam), to craft and camouflage physical-world 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. Experimental evaluation shows that, in both digital and physical-world scenarios, adversarial examples crafted by AdvCam are well camouflaged and highly stealthy, while remaining effective in fooling state-of-the-art DNN image classifiers. Hence, AdvCam is a flexible approach that can help craft stealthy attacks to evaluate the robustness of DNNs. AdvCam can also be used to protect private information from being detected by deep learning systems.