Radio frequency fingerprint identification based on stream differential constellation trace figures

Abstract

Recently, radio frequency fingerprint (RFF) technique, characterized by unique hardware impairments, has seen vast attention for specific transmitter identification and authorized access. Differential constellation trace figure (DCTF) emerges as an effective image-based RFF method, which forms a stable constellation figure by performing a key differential process. Previous studies that are based on a single differential interval (DI) are susceptible to noise, which leads to under-performance in cases with low signal-to-noise ratios (SNRs). To address this problem, this paper proposes a stream DCTFs scheme that mainly consists of (i) RFF extraction deriving from numerous DIs, (ii) devising a feature reduction method containing feature importance ranking (FR) and feature set selection (FS), and (iii) extensive experimental evaluations. When the SNR ranges from 5 dB up to 10 dB, the classification results reach 96.3% and 98.4% respectively among 54 ZigBee devices, which are about 40% and 20% higher than existing DCTF-based methods. Moreover, the authentication accuracy reaches 100% in verification.