A Generalized Radio Frequency Fingerprint-Based Wireless Device Identification Using Siamese-Based Neural Network
Rundong Jiang, Jun Peng Hu, He Huang, Chudi Zhang, Lei Wang, Shiyou Xu · IEEE Sensors Journal · 2024
Radio frequency (RF) fingerprint (RFF) refers to a unique hardware-related feature of RF devices, characterized by nonreproducible physical characteristics. This feature makes RFF suitable for equipment identity authentication in wireless communication, particularly in the Internet of Things (IoT). Therefore, we propose a more generalized and intuitive definition of the RFF, namely, the differences between the received and ideal RF signals. The ideal RF signal is defined as having the same input information source, encoding, and modulation schemes as the received signal, but without any influences from hardware devices or wireless transmission channels. Our approach begins by analyzing the effects of transmission channels, such as attenuation, dispersion, multipath propagation, and noise, treating them as a series of processes. We represent both the received and ideal signals in a designed multidomain space. We then develop a Siamese-based neural network to extract features from the multidomain representations of paired signals simultaneously. A difference block is used to eliminate common features and retain the expected generalized RFF (GRFF). Identification is achieved by treating each device as a specific class, utilizing a softmax classifier. Besides, we introduce a two-stage strategy involving nearest neighbor and particle swarm optimization to discriminate the out-of-distribution signals. Experiments are carried out using a public ADS-B signal dataset, and the trained network achieves a classification accuracy of 99.13% on a test dataset with 7442 samples from 58 classes in total and out-of-distribution detection accuracy of 95.45% under a class confidence of 0.96 on 5560 samples from additional 206 classes.