RF Fingerprint Classification With Combinatorial-Randomness-Based Power Amplifiers and Convolutional Neural Networks: Secure analog/RF electronics and electromagnetics

Abstract

The growth of the IoT requires more comprehensive security measures than ever. RF fingerprinting (RFF) utilizes features in the signals and waveforms from transmitters’ physical-layer imperfections to classify and authenticate devices. To prevent attacks from impersonators, combinatorial randomness is exploited to augment the RF fingerprints with a high-efficiency PA for IoT applications. By enabling different subsets of thinly sliced PA elements, the transmitter can be reconfigured with 220 subsets that exhibit distinctive RF fingerprints for signal analysis at the edge. In this work, a combinatorial-randomness-based PA was implemented in a BLE system. The BLE packets’ in-phase and quadrature samples transmitted from each configuration are collected with different SNRs to emulate the environmental changes in communication channels. A lightweight convolutional neural network (CNN) classifier demonstrates the possibility of accurate and fast inference of unique features in the IoT environment, which our approach exploits to enable on-chip time-varying RF fingerprints.