A multi-feature fusion approach for physical layer authentication in LEO satellites

Abstract

Spatial information networks (SINs) have emerged as a means to enhance the expanse and dependability of communication and data transmission services. SINs rely on satellite systems to provide these services, among which low earth orbit (LEO) satellites are widely concerned because of their advantages of low orbital altitude, small network transmission delay, small path loss, and high signal strength. However, due to the frequent switching of communication links between LEO satellites and the ground, the authentication mechanism of the ground users to the satellites is vulnerable to spoofing attacks, and the traditional upper layer authentication method based on encryption usually requires a lot of overhead and delay. In this case, the lightweight physical layer authentication (PLA) mechanism utilizes the inherent distinctiveness and unpredictable nature of channel physical properties, serving as a vital application in SINs for ensuring authentication. Therefore, our work introduces a PLA method incorporating multi-feature integration, aimed at delivering effective identity verification tailored for LEO satellites. The approach employs doppler frequency shift (DS), angles of arrival (AOAs), and received power (RP) features, fusing an support vector machine (SVM) classifier, to distinguish between legal and illegal satellites in different simulation scenarios. The satellite toolkit (STK) is used to collect data from the actual orbit of satellites and assess the efficacy of the scheme. The findings indicate that the scheme offers enhanced authentication capabilities.