Machine Learning Methods for Device Identification Using Wireless Fingerprinting

ML module using commonly used RESTful framework. Explosion in the number of connected IoT devices brought Comprehensive ML module based on both classical and increasing concerns for IoT systems security [1]. Industrial deep learning methods is implemented as a cloud-based service. IoT systems are particularly vulnerable, since IoT devices The ML module employs representative methods for may participate in mission-critical industrial control processes supervised device identification due to the availability of [2]. In recent years, the IoT security methods that exploit a device IDs in the collected WF data sets. Due to different WFs combination of specific features unique to the device, called collected from NB-IoT and Wi-Fi devices, different MLAs fingerprints, and machine learning (ML) algorithms, became are considered for the two scenarios. The system is integrated increasingly popular [3]-[10]. In particular, wireless fingerprints and tested in our labs and an extensive device identification (WF) may be extracted at the physical (PHY) layer of a performance is presented and visualised. The setup is currently wireless receiver, based on the signals received from different being migrated to a real-world industrial IoT scenario, where wireless IoT devices [3], [4].