Eavesdropping and Jamming via Pilot Attacks in 5G Massive MIMO

Abstract

[Abstract] In thiswork, we investigate pilot attacks for 5G single-cell multi-user massive multipleinput multiple-output (MaMIMO) systems with a single-antenna active eavesdropper and a single-antenna jammer operating in time-division duplex (TDD) schemes. Firstly, we describe the attacks when the base station (BS) estimates the channel state information (CSI) based on the uplink pilot transmissions. Finally, we propose a reinforcement learning (RL)-based framework for maximizing the system sum rate that proved robust to the eavesdropping and jamming attacks