{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T17:58:18Z","timestamp":1762624698837,"version":"3.37.3"},"reference-count":38,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T00:00:00Z","timestamp":1630886400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018525","name":"Key Research and Development Program of Sichuan Province","doi-asserted-by":"publisher","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}],"id":[{"id":"10.13039\/501100018525","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tianjin Intelligent Manufacturing Special Fund Project","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin City","doi-asserted-by":"publisher","award":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"],"award-info":[{"award-number":["2019YFB2101700","62172297","61902276","21SYSX0082","20201159","LP190100676","19JCQNJC00200"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Security and Communication Networks"],"published-print":{"date-parts":[[2021,9,6]]},"abstract":"<jats:p>With the extensive application of artificial intelligence technology in 5G and Beyond Fifth Generation (B5G) networks, it has become a common trend for artificial intelligence to integrate into modern communication networks. Deep learning is a subset of machine learning and has recently led to significant improvements in many fields. In particular, many 5G-based services use deep learning technology to provide better services. Although deep learning is powerful, it is still vulnerable when faced with 5G-based deep learning services. Because of the nonlinearity of deep learning algorithms, slight perturbation input by the attacker will result in big changes in the output. Although many researchers have proposed methods against adversarial attacks, these methods are not always effective against powerful attacks such as CW. In this paper, we propose a new two-stream network which includes RGB stream and spatial rich model (SRM) noise stream to discover the difference between adversarial examples and clean examples. The RGB stream uses raw data to capture subtle differences in adversarial samples. The SRM noise stream uses the SRM filters to get noise features. We regard the noise features as additional evidence for adversarial detection. Then, we adopt bilinear pooling to fuse the RGB features and the SRM features. Finally, the final features are input into the decision network to decide whether the image is adversarial or not. Experimental results show that our proposed method can accurately detect adversarial examples. Even with powerful attacks, we can still achieve a detection rate of 91.3%. Moreover, our method has good transferability to generalize to other adversaries.<\/jats:p>","DOI":"10.1155\/2021\/5395705","type":"journal-article","created":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T20:05:07Z","timestamp":1631045107000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["FNet: A Two-Stream Model for Detecting Adversarial Attacks against 5G-Based Deep Learning Services"],"prefix":"10.1155","volume":"2021","author":[{"given":"Guangquan","family":"Xu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin 300350, China"},{"name":"School of Big Data, Qingdao Huanghai University, Qingdao 266555, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7124-0536","authenticated-orcid":true,"given":"Guofeng","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin 300350, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Litao","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Big Data, Qingdao Huanghai University, Qingdao 266555, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiqi","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin 300350, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computing, Macquarie University, North Ryde 2113, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9104-2975","authenticated-orcid":true,"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin 300350, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113240"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"first-page":"173","article-title":"Deep speech 2: end-to-end speech recognition in English and Mandarin","author":"D. Amodei","key":"5"},{"issue":"23","key":"6","first-page":"1","article-title":"GluonCV and GluonNLP: deep learning in computer vision and natural language processing","volume":"21","author":"J. Guo","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/mci.2018.2840738"},{"key":"8","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780199285648.001.0001","volume-title":"Economic Transformations: General Purpose Technologies and Long-Term Economic Growth","author":"R. G. Lipsey","year":"2005"},{"article-title":"Machine learning for wireless networks with artificial intelligence: a tutorial on neural networks","year":"2017","author":"M. Chen","key":"9"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2837692"},{"key":"11","article-title":"The application of artificial intelligence at Chinese digital platform giants: baidu, alibaba and tencent","volume":"81","author":"K. Jia","year":"2018","journal-title":"ETLA Reports"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2021.3071405"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/percom45495.2020.9127389"},{"article-title":"A semi-black-box android adversarial sample attack framework against DLAAS","year":"2021","author":"G. Xu","key":"14"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"G. Hinton","key":"15"},{"article-title":"A study of the effect of jpg compression on adversarial images","year":"2016","author":"G. K. Dziugaite","key":"16"},{"key":"17","article-title":"Detecting adversarial image examples in deep neural networks with adaptive noise reduction","volume":"18","author":"B. Liang","year":"2018","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"I. J. Goodfellow","key":"18"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2012.2190402"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1117\/12.465263"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/mc.1998.4655281"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4440-4"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.170"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1145\/3190619.3190637"},{"article-title":"Intriguing properties of neural networks","year":"2013","author":"C. Szegedy","key":"26"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/sp.2017.49"},{"first-page":"2574","article-title":"DeepFool: a simple and accurate method to fool deep neural networks","author":"S.-M. Moosavi-Dezfooli","key":"28"},{"article-title":"Adversarial examples in the physical world","year":"2016","author":"A. Kurakin","key":"29"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/sp.2016.41"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00496"},{"article-title":"Detecting adversarial samples from artifacts","year":"2017","author":"R. Feinman","key":"32"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00116"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"K. Simonyan","key":"34"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"issue":"11","key":"36","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y. LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"article-title":"Adversarial robustness toolbox v1. 0.0","year":"2018","author":"M.-I. Nicolae","key":"37"},{"article-title":"On evaluating adversarial robustness","year":"2019","author":"N. Carlini","key":"38"}],"container-title":["Security and Communication Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/5395705.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/5395705.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/5395705.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T13:44:40Z","timestamp":1699451080000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/scn\/2021\/5395705\/"}},"subtitle":[],"editor":[{"given":"Benjamin","family":"Aziz","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,9,6]]},"references-count":38,"alternative-id":["5395705","5395705"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5395705","relation":{},"ISSN":["1939-0122","1939-0114"],"issn-type":[{"type":"electronic","value":"1939-0122"},{"type":"print","value":"1939-0114"}],"subject":[],"published":{"date-parts":[[2021,9,6]]}}}