The 5G networks are very important to support complex application by connecting different types of machines and devices, which provide the platform for different spoofing attacks. Traditional physical layer and cryptography authentication methods are facing problems in dynamic complex environment, including less reliability, security overhead also problem in predefined authentication system, giving protection and learn about time-varying attributes. In this paper, intrusion detection framework has been designed using various machine learning methods with the help of physical layer attributes and to provide more efficient system to increase the security. Machine learning methods for the intelligent intrusion detection are introduced, especially for supervised and non-supervised methods. Our machine learning based intelligent intrusion detection technique for the 5G and beyond networks is evaluated in terms of recall, precision, accuracy and f-value are validated for unpredictable dynamics and unknown conditions of networks.

中文翻译：

---

使用ML的5G及更高网络中入侵检测的新有效方法

5G网络通过连接不同类型的机器和设备来支持复杂的应用程序非常重要，这为不同的欺骗攻击提供了平台。传统的物理层和密码认证方法在动态复杂的环境中面临着很多问题，包括可靠性较低，安全性开销以及预定义的认证系统中存在的问题，提供保护并了解时变属性。在本文中，借助物理层属性的帮助，使用各种机器学习方法设计了入侵检测框架，并提供了更有效的系统来提高安全性。介绍了用于智能入侵检测的机器学习方法，特别是针对监督和非监督方法。