Radio Frequency Fingerprint Identification Based on Logarithmic Power Cosine Spectrum

Abstract

With the development of new Internet of Things (IoT) applications, such as unmanned ground vehicle (UGV), unmanned aerial vehicle (UAV), and unmanned surface vessel (USV), the security of wireless device identification is getting more and more attention. The radio frequency fingerprint (RFF) technology utilizes the unique hardware characteristics of the device for identity authentication, which overcomes the security risks of traditional authentication schemes based on distributable keys. In this paper, we propose an RFF identification scheme based on logarithmic power cosine spectrum for transient signals. We use the sliding window variance trajectory-based posterior probability density detection algorithm to improve the efficiency of transient signal detection, then adopt the discrete Fourier transform to extract the logarithmic envelope power spectrum of the transient signal, after that utilize the cosine transform to compresses the frequency domain features, and finally construct the 7-dimensional RFF feature vector. For the application scenario of USV, we acquire the radio frequency signals of 7 marine automatic identification systems (AIS) as the test dataset. The experimental results show that the proposed scheme can achieve ideal recognition accuracy using a Support Vector Machine as the classifier. Meanwhile, we use Principal Component Analysis to verify that the 7-dimensional RFF feature vector has good distinguishability for different wireless devices.

Keywords

• Physical layer security
• radio frequency fingerprinting
• spectral transformation
• machine learning