Physical Layer Authentication in Wireless Networks-Based Machine Learning Approaches

• Published in: Sensors (Basel, Switzerland) Switzerland), 2023-02, Vol.23 (4), p.1814
• Main Authors: Alhoraibi, Lamia, Alghazzawi, Daniyal, Alhebshi, Reemah, Rabie, Osama Bassam J
• Format: Article
• Language: English
• Subjects: Access control; Algorithms; Artificial intelligence; Authentication; Confidentiality; Cryptography; Deep learning; Internet of Things; Machine learning; Network security; physical layer authentication; physical layer security; Research methodology; Review; Security systems; signal classification; Signal processing; Spread spectrum; Systematic review; Telecommunication systems; Ubiquitous computing; Wireless access points; wireless communication; Wireless communication systems; Wireless communications; Wireless networks
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23041814

The physical layer security of wireless networks is becoming increasingly important because of the rapid development of wireless communications and the increasing security threats. In addition, because of the open nature of the wireless channel, authentication is a critical issue in wireless communications. Physical layer authentication (PLA) is based on distinctive features to provide information-theory security and low complexity. However, although many researchers are interested in the PLA and how it might be used to improve wireless security, there is surprisingly little literature on the subject, with no systematic overview of the current state-of-the-art PLA and the main foundations involved. Therefore, this paper aims to determine and systematically compare existing studies in the physical layer authentication. This study showed whether machine learning approaches in physical layer authentication models increased wireless network security performance and demonstrated the latest techniques used in PLA. Moreover, it identified issues and suggested directions for future research. This study is valuable for researchers and security model developers interested in using machine learning (ML) and deep learning (DL) approaches for PLA in wireless communication systems in future research and designs.