Radio Frequency Fingerprint Identification for LoRa Using Spectrogram and CNN

TL;DR

This paper presents a spectrogram and CNN-based radio frequency fingerprinting method for LoRa devices, demonstrating high accuracy and effective CFO compensation in real-world experiments.

Contribution

The study introduces a novel spectrogram-based RFFI scheme for LoRa, incorporating CFO compensation and a hybrid classifier to improve identification accuracy.

Findings

Achieved 97.61% classification accuracy with 20 LoRa devices.

Spectrogram-based approach outperforms IQ and FFT-based methods.

Effective CFO compensation enhances system stability.

Abstract

Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique that relies on intrinsic hardware characteristics of wireless devices. We designed an RFFI scheme for Long Range (LoRa) systems based on spectrogram and convolutional neural network (CNN). Specifically, we used spectrogram to represent the fine-grained time-frequency characteristics of LoRa signals. In addition, we revealed that the instantaneous carrier frequency offset (CFO) is drifting, which will result in misclassification and significantly compromise the system stability; we demonstrated CFO compensation is an effective mitigation. Finally, we designed a hybrid classifier that can adjust CNN outputs with the estimated CFO. The mean value of CFO remains relatively stable, hence it can be used to rule out CNN predictions whose estimated CFO falls out of the range. We performed experiments in real wireless environments using 20 LoRa devices under test (DUTs) and a Universal Software Radio Peripheral (USRP) N210 receiver. By comparing with the IQ-based and FFT-based RFFI schemes, our spectrogram-based scheme can reach the best classification accuracy, i.e., 97.61% for 20 LoRa DUTs.