LEO Satellite Authentication using Physical Layer Features with Support Vector Machine

Abstract

To overcome terrestrial network coverage limitations, low-earth orbit (LEO) satellites aim to provide worldwide connectivity for sixth generation (6G) networks. However, LEO satellites are vulnerable to spoofing attacks. To overcome this limitation, physical layer authentication (PLA) can be employed to provide effective satellite authentication by utilizing physical features. In this paper, an adaptive PLA scheme is proposed using a single-class classification support vector machine (SCC-SVM) with received power (RP) and Doppler frequency spread (DS) features. The proposed scheme is evaluated for on-the-pause satellite communication (OTPSC) systems. The results obtained show that using both RP and DS as features provides better authentication performance than when they are used individually.