Skip to main content Skip to main navigation

Publication

Multi-Feature Physical Layer Authentication for URLLC based on Linear Supervised Learning

Andreas Weinand; Christoph Lipps; Miachel Karrenbauer; Hans Dieter Schotten
In: Proceedings of the European Conference on Networks and Communications (EuCNC) and the 6G Summit. European Conference on Networks and Communications (EuCNC-2023), June 6-9, Gothenburg, Sweden, IEEE, 6/2023.

Abstract

Physical Layer Authentication (PLA) can be a lightweight alternative to conventional security schemes such as certifi cates or Message Authentication Codes (MACs) for secure message transmission within Ultra Reliable Low Latency Communication (URLLC) scenarios. Single features such as Received Signal Strength Indicator (RSSI) are however not providing suffi cient authentication accuracy. Therefore, multi-feature techniques for PLA are introduced within this work and evaluated using a Universal Software Radio Peripheral (USRP) based testbed in a mobile URLLC campus network scenario. Linear supervised classifi cation is proposed for PLA and evaluated under diff erent attacker scenarios. The results show promising authentication performances in most of the evaluated senarions and can be increased by the application of multi-feature authentication.

Projekte