Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles
arXiv:2003.08757
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 (\emph{AdvCam}), to craft and camouflage physical-world adversarial examples into natural styles that appear legitimate to human observers. Specifically, \emph{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 \emph{AdvCam} are well camouflaged and highly stealthy, while remaining effective in fooling state-of-the-art DNN image classifiers. Hence, \emph{AdvCam} is a flexible approach that can help craft stealthy attacks to evaluate the robustness of DNNs. \emph{AdvCam} can also be used to protect private information from being detected by deep learning systems.
arXiv commentAccepted to CVPR2020
References in corpus (9)
- Synthesizing Robust Adversarial Examples
- Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
- Robust Physical-World Attacks on Deep Learning Models
- Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
- Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
- On the Convergence and Robustness of Adversarial Training
- Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
- Residual Convolutional CTC Networks for Automatic Speech Recognition
- Adversarial T-shirt! Evading Person Detectors in A Physical World