Abstract—Spoofing Attack (SA) is a challenging issue in mobile wireless communication especially with huge traffic in 5G and beyond where attacker inserts counterfeit data with false identification to intercept a valid transmission. Detection and corrective action become very important in these cases. A potential method to prevent identity spoofing threats is channel-based Physical-Layer (PL) privacy. It is of interest to a broad spectrum of people and organizations engaged in network administration and computer security. In this work, channel-based SA identification method is proposed to prevent serious consequences. The Physical Layer (PL) properties are utilized in order to detect SA. As a unique channel feature, the Prime Elements of a Digital Channel Representation (PE-DCR) are identified. In this work, a detection method is developed which is built on PEDCR to detect SA in stable and varying radio surroundings. The challenge of SA detection is changed into a 1st-Class Categorization (1-CC) issue for the changing radio setting where the channel covariance is fluctuating. An active detection system based on Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks (NN) as Back Propagation Forward Scheme (BPFS) is proposed to effectively manage this issue. Results from simulations validate the viability of the proposed detection methods. The proposed method achieved detection accuracy of 80%.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.