当前位置: X-MOL 学术IEEE Wirel. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Learning for Secure Wireless Communications in Cyber Physical Systems
IEEE Wireless Communications ( IF 10.9 ) Pub Date : 6-20-2022 , DOI: 10.1109/mwc.2022.9801737
Yi Qian 1
Affiliation  

Deep learning has strong potential using data-driven solutions to improve the performance of cyber physical systems (CPS) in utilizing limited spectrum resources in wireless communications. Deep learning is also a powerful method of data exploration to learn about “normal” and “abnormal” behavior according to how CPS components and devices interact with each other. Furthermore, deep learning methods are important in predicting new attacks, which are often mutations of previous attacks because they can intelligently predict future unknown attacks by learning from existing examples. The topic of deep learning for secure wireless communications in CPS has gained much momentum in the industry and the research community very recently. In this issue of IEEE Wireless Communications, we are pleased to present a Feature Topic on “Deep Learning Driven Secure Communication for Cyber Physical Systems” to bring together researchers, industry practitioners, and individuals working on the related areas to address some of the technical challenges faced by the research topics. This Feature Topic includes a collection of 10 articles chosen by Guest Editors W. Wei, C.-H. Hsu, V. Piuri, and A. Rayes. We are also pleased to present a second Feature Topic on “Enhanced Fronthaul for 5G and Beyond” that includes a collection of four articles chosen by Guest Editors Y. Luo, P. Chanclou, K. E. Skouby, H. Zhao, and K. Asaka. Thanks to the two Guest Editor teams who did an excellent job in editing these two Feature Topics for our readers. Please stay tuned for new developments in these research areas, and read the editorials and articles in the two Feature Topics.

中文翻译:


网络物理系统中安全无线通信的深度学习



深度学习在使用数据驱动的解决方案来提高网络物理系统(CPS)在无线通信中利用有限频谱资源的性能方面具有巨大的潜力。深度学习也是一种强大的数据探索方法,可以根据 CPS 组件和设备之间的交互方式来了解“正常”和“异常”行为。此外,深度学习方法对于预测新的攻击非常重要,这些攻击通常是先前攻击的突变,因为它们可以通过从现有示例中学习来智能地预测未来的未知攻击。最近,CPS 中安全无线通信的深度学习主题在业界和研究界获得了很大的发展势头。在本期 IEEE 无线通信中,我们很高兴提出“网络物理系统的深度学习驱动的安全通信”专题,将研究人员、行业从业者和从事相关领域工作的个人聚集在一起,共同解决一些技术挑战面临的研究课题。本专题包括客座编辑 W. Wei, C.-H. 精选的 10 篇文章。 Hsu、V. Piuri 和 A. Rayes。我们还很高兴推出第二个专题主题“5G 及以上的增强型前传”,其中包括客座编辑 Y. Luo、P. Chanclou、KE Skouby、H. Zhu 和 K. Asaka 精选的四篇文章。感谢两位客座编辑团队为我们的读者出色地编辑了这两个专题。请继续关注这些研究领域的新进展,并阅读两个专题中的社论和文章。
更新日期:2024-08-26
down
wechat
bug