{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T05:12:22Z","timestamp":1769317942178,"version":"3.49.0"},"reference-count":40,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971426"],"award-info":[{"award-number":["61971426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Synthetic aperture radar (SAR) can perform observations at all times and has been widely used in the military field. Deep neural network (DNN)-based SAR target recognition models have achieved great success in recent years. Yet, the adversarial robustness of these models has received far less academic attention in the remote sensing community. In this article, we first present a comprehensive adversarial robustness evaluation framework for DNN-based SAR target recognition. Both data-oriented metrics and model-oriented metrics have been used to fully assess the recognition performance under adversarial scenarios. Adversarial training is currently one of the most successful methods to improve the adversarial robustness of DNN models. However, it requires class labels to generate adversarial attacks and suffers significant accuracy dropping on testing data. To address these problems, we introduced adversarial self-supervised learning into SAR target recognition for the first time and proposed a novel unsupervised adversarial contrastive learning-based defense method. Specifically, we utilize a contrastive learning framework to train a robust DNN with unlabeled data, which aims to maximize the similarity of representations between a random augmentation of a SAR image and its unsupervised adversarial example. Extensive experiments on two SAR image datasets demonstrate that defenses based on adversarial self-supervised learning can obtain comparable robust accuracy over state-of-the-art supervised adversarial learning methods.<\/jats:p>","DOI":"10.3390\/rs13204158","type":"journal-article","created":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T23:25:15Z","timestamp":1634513115000},"page":"4158","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Adversarial Self-Supervised Learning for Robust SAR Target Recognition"],"prefix":"10.3390","volume":"13","author":[{"given":"Yanjie","family":"Xu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Jin","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Remote Sensing Information, Beijing 100092, China"}]},{"given":"Lin","family":"Lei","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Kefeng","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Gangyao","family":"Kuang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Tait, P. (2005). Introduction to Radar Target Recognition, IET.","DOI":"10.1049\/PBRA018E"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1109\/JSTARS.2016.2520518","article-title":"Man-made target detection from polarimetric sar data via nonstationarity and asymmetry","volume":"9","author":"Xiang","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shao, J., Qu, C., and Li, J. (2017, January 13\u201314). A performance analysis of convolutional neural network models in sar target recognition. Proceedings of the 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), Beijing, China.","DOI":"10.1109\/BIGSARDATA.2017.8124917"},{"key":"ref_4","unstructured":"Keydel, E.R., Lee, S.W., and Moore, J.T. (1996, January 10). Mstar extended operating conditions: A tutorial. Proceedings of the Algorithms for Synthetic Aperture Radar Imagery III, Orlando, FL, USA."},{"key":"ref_5","first-page":"364","article-title":"Convolutional neural network with data augmentation for sar target recognition","volume":"13","author":"Ding","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.procs.2019.02.036","article-title":"All convolutional neural networks for radar-based precipitation nowcasting","volume":"150","author":"Ayzel","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_7","first-page":"928","article-title":"Architecture design of deep convolutional neural network for sar target recognition","volume":"23","author":"Gu","year":"2018","journal-title":"J. Image Graph."},{"key":"ref_8","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1109\/TGRS.2020.2999962","article-title":"Assessing the threat of adversarial examples on deep neural networks for remote sensing scene classification: Attacks and defenses","volume":"59","author":"Xu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (2016, January 27\u201330). Deepfool: A simple and accurate method to fool deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref_12","unstructured":"Kurakin, A., Goodfellow, I., and Bengio, S. (2017, January 24\u201326). Adversarial machine learning at scale. Proceedings of the 5th International Conference on Learning Representations, ICLR - Conference T rack Proceedings, Toulon, France."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., and Frossard, P. (2017, January 21\u201326). Universal adversarial perturbations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1109\/JSTARS.2020.3038683","article-title":"Adversarial examples for cnn-based sar image classification: An experience study","volume":"14","author":"Li","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/JSTARS.2020.3039235","article-title":"Robust sar automatic target recognition via adversarial learning","volume":"14","author":"Guo","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_16","unstructured":"Chen, T., Liu, S., Chang, S., Cheng, Y., Amini, L., and Wang, Z. (2018, January 18). Adversarial robustness: From self-supervised pre-training to fine-tuning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA."},{"key":"ref_17","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., and Song, D. (2019). Using self-supervised learning can improve model robustness and uncertainty. arXiv."},{"key":"ref_18","unstructured":"Jiang, Z., Chen, T., Chen, T., and Wang, Z. (2020). Robust pre-training by adversarial contrastive learning. arXiv."},{"key":"ref_19","unstructured":"Alayrac, J.-B., Uesato, J., Huang, P.-S., Fawzi, A., Stanforth, R., and Kohli, P. (2018, January 18). Are labels required for improving adversarial robustness?. Proceedings of the Neural Information Processing Systems, Salt Lake City, UT, USA."},{"key":"ref_20","unstructured":"Kim, M., Tack, J., and Hwang, S.J. (2020). Adversarial self-supervised contrastive learning. arXiv."},{"key":"ref_21","unstructured":"Bui, A., Le, T., Zhao, H., Montague, P., Camtepe, S., and Phung, D. (2021). Understanding and achieving efficient robustness with adversarial contrastive learning. arXiv."},{"key":"ref_22","unstructured":"Athalye, A., Carlini, N., and Wagner, D. (2018). Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ortiz-Jim\u00e9nez, G., Modas, A., Moosavi-Dezfooli, S.-M., and Frossard, P. (2020). Optimism in the face of adversity: Understanding and improving deep learning through adversarial robustness. arXiv.","DOI":"10.1109\/JPROC.2021.3050042"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Czaja, W., Fendley, N., Pekala, M., Ratto, C., and Wang, I.-J. (2018, January 6\u20139). Adversarial examples in remote sensing. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, WA, USA.","DOI":"10.1145\/3274895.3274904"},{"key":"ref_25","unstructured":"Liu, A., Liu, X., Guo, J., Wang, J., Ma, Y., Zhao, Z., Gao, X., and Xiao, G. (2021). A comprehensive evaluation framework for deep model robustness. arXiv."},{"key":"ref_26","unstructured":"He, W., Li, B., and Song, D. (May, January 30). Decision boundary analysis of adversarial examples. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_27","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv."},{"key":"ref_28","unstructured":"Fong, R., Patrick, M., and Vedaldi, A. (November, January 27). Understanding deep networks via extremal perturbations and smooth masks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1648","DOI":"10.1109\/TCSVT.2010.2087432","article-title":"Just noticeable difference for images with decomposition model for separating edge and textured regions","volume":"20","author":"Liu","year":"2010","journal-title":"IEEE Trans. Circuits. Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tack, J., Yu, S., Jeong, J., Kim, M., Hwang, S.J., and Shin, J. (2021). Consistency regularization for adversarial robustness. arXiv.","DOI":"10.1609\/aaai.v36i8.20817"},{"key":"ref_31","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201319). A simple framework for contrastive learning of visual representations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA."},{"key":"ref_32","unstructured":"Zhang, H., Yu, Y., Jiao, J., Xing, E., El Ghaoui, L., and Jordan, M. (2019, January 10\u201315). Theoretically principled trade-off between robustness and accuracy. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_33","unstructured":"Wong, E., Rice, L., and Kolter, J.Z. (2020). Fast is better than free: Revisiting adversarial training. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Hou, X., Ao, W., Song, Q., Lai, J., Wang, H., and Xu, F. (2020). Fusar-ship: Building a high-resolution sar-ais matchup dataset of gaofen-3 for ship detection and recognition. Sci. China Inf. Sci., 63.","DOI":"10.1007\/s11432-019-2772-5"},{"key":"ref_35","unstructured":"Croce, F., and Hein, M. (, January November). Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. Proceedings of the International Conference on Machine Learning, Las Vegas, NV, USA."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_38","unstructured":"Howard, A., Zhmoginov, A., Chen, L.-C., Sandler, M., and Zhu, M. (2018). Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018). Shufflenet v2: Practical guidelines for efficient cnn architecture design. arXiv.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Feng, S., Ji, K., Ma, X., Zhang, L., and Kuang, G. (2021). Target region segmentation in sar vehicle chip image with acm net. IEEE Geosci. Remote Sens. Lett., 1\u20135.","DOI":"10.1109\/LGRS.2021.3085188"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/20\/4158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:16:30Z","timestamp":1760166990000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/20\/4158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":40,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["rs13204158"],"URL":"https:\/\/doi.org\/10.3390\/rs13204158","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,17]]}}}