An Empirical Study Towards SAR Adversarial Examples
Zhiwei Zhang, Shuowei Liu, Xunzhang Gao, Yujia Diao · 2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · 2022
Adversarial attack and adversarial detection have become a hot issue in the field of deep learning based image forensics. However, current researches mainly focus on optical images. Synthetic aperture radar (SAR) images are quite different from the optical images in both imaging mechanism and data structure. This paper aims to study adversarial attack and adversarial detection for SAR images. Firstly, we analyze the distribution characteristics of SAR adversarial examples (AEs) in both output space and feature space by transferring optical attacks. In order to match the digital perturbation with the scattering energy of target, we then propose a generation method of SAR AEs with regional constraint. Experiments show that the proposed method generates SAR AEs that can evade current adversarial detection at the cost of attack success rate. Finally, we point out an open issue that decreasing the perturbation scale leads to the degradation of adversarial detection against both optical AEs and SAR AEs.