Mobile physical layer spoofing detection based on sparse representation

Abstract

Recently, physical layer authentication techniques are emerging to detect spoofing attacks in wireless networks based on high consistency between two legitimate successive channel information. However, this high consistency is not always available, especially in dynamic networks, such as mobile scenarios. In this study, the authors propose a physical layer spoofing detection scheme based on sparse signal processing that exploit sparse representation and Savitzky-Golay filter, and use machine learning strategy to improve the spoofing detection accuracy under the case of low channel consistency. Simulation results show that the proposed technique can significantly improve the detection accuracy under the condition of low channel consistency.