@inproceedings{94e31f4233284856be8395ab87748c65,
title = "Naturalistic Physical Adversarial Patch for Object Detectors",
abstract = "Most prior works on physical adversarial attacks mainly focus on the attack performance but seldom enforce any restrictions over the appearance of the generated adversarial patches. This leads to conspicuous and attention-grabbing patterns for the generated patches which can be easily identified by humans. To address this issue, we propose a method to craft physical adversarial patches for object detectors by leveraging the learned image manifold of a pretrained generative adversarial network (GAN) (e.g., BigGAN and StyleGAN) upon real-world images. Through sampling the optimal image from the GAN, our method can generate natural looking adversarial patches while maintaining high attack performance. With extensive experiments on both digital and physical domains and several independent subjective surveys, the results show that our proposed method produces significantly more realistic and natural looking patches than several state-of-the-art baselines while achieving competitive attack performance.",
author = "Hu, {Yu Chih Tuan} and Kung, {Bo Han} and Tan, {Daniel Stanley} and Chen, {Jun Cheng} and Hua, {Kai Lung} and Cheng, {Wen Huang}",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 ; Conference date: 11-10-2021 Through 17-10-2021",
year = "2021",
doi = "10.1109/ICCV48922.2021.00775",
language = "English",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7828--7837",
booktitle = "Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021",
address = "美國",
}