Light Weight CSI-Based Physical Layer Authentication Model for IoT Networks

This study introduces a novel physical layer authentication technique for Internet of Things (IoT) networks, leveraging Channel State Information (CSI) data from Wi-Fi signals to distinguish between authorized and unauthorized nodes, thereby enhancing security without compromising performance. Its novelty lies in the integrated framework that employs Non-negative Matrix Factorization (NMF) for efficient feature selection and a Gaussian Mixture Model (GMM) to identify complex patterns within the CSI data, adapting to the dynamic nature of IoT networks. The model demonstrates exceptional classification proficiency, achieving an accuracy rate of 99.83% and a recall of 100%, which is important for critical applications such as cybersecurity and anomaly detection, where identifying threats is of key importance. Furthermore, the F1-score of 99.84% reflects a strong balance between precision and recall. From a practical standpoint, the system is designed for efficiency and minimal resource consumption, exhibiting good computational efficiency, reduced training duration, and lower energy consumption compared to more complex architectures such as CNN and CNN+LSTM. This balance of high performance and resource efficiency makes it particularly suitable for deployment in resource-constrained IoT environments.