Attributed Scattering Center Guided Adversarial Attack for DCNN SAR Target Recognition

被引:0
作者
Zhou, Junfan [1 ]
Feng, Sijia [1 ]
Sun, Hao [1 ]
Zhang, Linbin [1 ]
Kuang, Gangyao [1 ]
机构
[1] Natl Univ Def Technol, State Key Lab Complex Electromagnet Environm Effec, Changsha 410073, Peoples R China
基金
中国国家自然科学基金;
关键词
Image reconstruction; Scattering; Radar polarimetry; Perturbation methods; Synthetic aperture radar; Imaging; Shape; Adversarial attack (AA); attributed scattering center (ASC); deep convolutional neural networks (DCNNs); spatial transformation; synthetic aperture radar (SAR);
D O I
暂无
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Recently, deep learning has made significant progress in synthetic aperture radar automatic target recognition (SAR ATR). However, deep convolutional neural networks (DCNNs) are discovered to be susceptible to carefully crafted adversarial perturbations. Regarding the unique scattering mechanism in SAR imaging, the scattering feature such as attributed scattering centers (ASCs) should be deeply considered in the adversarial attack (AA) algorithms for DCNNs in SAR ATR. In this letter, an AA algorithm named ASC-STA is proposed to take advantage of the powerful SAR imaging property characterization capability of the ASC model. Considering the imaging characteristic that is presented in the ASC model, the spatial transformation module is specially designed to be performed on the strong backscattering structures guided by the reconstruction image of the ASC model. Spatial transformation shifts the robust scattering point features via altering the locally gray-scale relationships of the target microstructures in SAR images. Besides, a modified shape context evaluated metric is established to assess the validity of the feature alternation process. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) database demonstrate that the proposed method achieves a high success rate without complex parameter settings and generates the perturbed image in high image quality. Compared with the norm-based AA algorithms, which are not involved with ASCs, the point feature of the original image is efficiently altered. At the same time, the perturbations are focused on the target regions accurately.
引用
收藏
页数:5
相关论文
共 50 条
[41]   Target Recognition in Synthetic Aperture Radar Images via Matching of Attributed Scattering Centers [J].
Ding, Baiyuan ;
Wen, Gongjian ;
Huang, Xiaohong ;
Ma, Conghui ;
Yang, Xiaoliang .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2017, 10 (07) :3334-3347
[42]   Causal Adversarial Autoencoder for Disentangled SAR Image Representation and Few-Shot Target Recognition [J].
Guo, Qian ;
Xu, Huilin ;
Xu, Feng .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 :1-14
[43]   Polarimetric Target Decomposition Based on Attributed Scattering Center Model for Synthetic Aperture Radar Targets [J].
Duan, Jia ;
Zhang, Lei ;
Xing, Mengdao ;
Wu, Yifeng ;
Wu, Min .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (12) :2095-2099
[44]   A SAR Target Recognition Algorithm Based on Guided Filter Reconstruction and Denoising Sparse Autoencoder [J].
Wang J. ;
Qin C. ;
Yang K. ;
Ren P. .
Binggong Xuebao/Acta Armamentarii, 2020, 41 (09) :1861-1870
[45]   Serialized orthogonal matching pursuit fusing image domain information for attributed scattering center extraction in SAR images [J].
Long, Bo ;
Wang, Feng .
JOURNAL OF INFRARED AND MILLIMETER WAVES, 2024, 43 (06) :784-796
[46]   TAN: A Transferable Adversarial Network for DNN-Based UAV SAR Automatic Target Recognition Models [J].
Du, Meng ;
Sun, Yuxin ;
Sun, Bing ;
Wu, Zilong ;
Luo, Lan ;
Bi, Daping ;
Du, Mingyang .
DRONES, 2023, 7 (03)
[47]   Generative Adversarial Networks for SAR Automatic Target Recognition and Classification Models Enhanced Explainability: Perspectives and Challenges [J].
Remusati, Heloise ;
Le Caillec, Jean-Marc ;
Schneider, Jean-Yves ;
Petit-Frere, Jacques ;
Merlet, Thomas .
REMOTE SENSING, 2024, 16 (14)
[48]   Template-based universal adversarial attack for synthetic aperture radar automatic target recognition network [J].
Liu, Wei ;
Wan, Xuanshen ;
Niu, Chaoyang ;
Lu, Wanjie ;
Li, Yuanli .
IET RADAR SONAR AND NAVIGATION, 2025, 19 (01)
[49]   DESIGN OF THE PHYSICALLY INTERPRETABLE SAR TARGET RECOGNITION NETWORK COMBINED WITH ELECTROMAGNETIC SCATTERING CHARACTERISTICS [J].
Li, Yi ;
Du, Lan .
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, :4988-4991
[50]   Non-Cooperative SAR Automatic Target Recognition Based on Scattering Centers Models [J].
Araujo, Gustavo F. ;
Machado, Renato ;
Pettersson, Mats I. .
SENSORS, 2022, 22 (03)