Lightweight Radio Frequency Fingerprint Identification Scheme for V2X Based on Temporal Correlation

Radio frequency fingerprinting identification (RFFI) is a promising physical layer authentication technique based on the inherent hardware defects of transmitters, yet there are bottlenecks in its application to vehicular networks. In this paper, we focus on the concerns of data dependency, channel effects, signal representation, and model efficiency to propose a lightweight RFFI scheme for vehicle-to-everything (V2X) communication based on temporal correlation. Specifically, modified gramian angular filed (MAGF) and Markov probability transition matrix with temporal dependency (MTTD) are proposed for signal representation to mine the temporal information related to device identity in terms of angular variation trajectory and first-order Markov transition probabilities, respectively. Due to the superiority of the proposed signal representation, paired with the customized pre-processing design, a lightweight feature extractor can achieve satisfactory RFFI performance in a very short time. We performed a comprehensive complexity analysis of existing models in the field and validated the proposed scheme using thirteen V2X devices in real wireless environments. In addition, the generalizability of the proposed pre-processing and representation method is demonstrated by testing on different deep learning models.