Rigorous Analysis of Data Orthogonalization for Self-Organizing Maps in Machine Learning Cyber Intrusion Detection for LoRa Sensors

Abstract

In this article, a novel unsupervised machine learning (ML) algorithm is presented for the expeditious radio frequency (RF) fingerprinting of long range (LoRa)-modulated chirps. Identification based on the received signal strength indicator (RSSI) alone is unlikely to yield a robust means of authentication for critical infrastructure deployments. This is especially true for LoRa, a low-power and LoRa wireless Internet-of-Things (IoT) air-interface technology, where modulated chirps have constant envelope power and correlated in-phase/quadrature (I/Q) samples when the chirps are directly extracted. This makes traditional cyber intrusion detection techniques via a convolutional neural network (CNN) impractical. Moreover, we also prove that such correlation leads to an orthogonally inseparable dataset, due to which classification becomes intractable. Therefore, we propose an efficient way to produce self-organizing maps (SOMs) of LoRa transmitters (TXs) and a potential rogue node prior to CNN classification. This approach offers SOM orthogonalization, thus minimizing the mean square error (MSE) within the CNN using our specially constituted SOM engine for precisely profiling each LoRa TX. This method demonstrates cent-percent success in recognizing each LoRa TX as either being a legitimate device or a rogue.