Machine Learning-based Robust Physical Layer Authentication Using Angle of Arrival Estimation

In this paper, we study the potential use of the angle of arrival (AoA) as a feature for performing robust, machine learning (ML) based physical layer authentication (PLA). In fact, whereas most previous research on PLA relies on physical properties such as channel state information or received signal strength, the use of the AoA in this context is not yet extensively researched from a robustness point of view, i.e., as the means to provide resistance to impersonation (location spoofing) attacks. In this study, we first prove that an effective impersonation attack on AoA estimation can only be done under very stringent conditions on the attacker in terms of location and hardware capabilities, and thus, the AoA can in many scenarios be used as a robust feature for authentication. In addition, we utilize machine learning in our study to provide lightweight, model-free, intelligent authentication. We demonstrate the effectiveness of the proposed PLA solutions by running the algorithms on experimental outdoor massive multiple input multiple output data.