Adaptive Beam Management for Secure mmWave Communications using Software-Defined Radios

mmWave systems leverage beamforming to generate narrow, high-powered beams for overcoming the increased path loss in the mmWave spectrum. These beams are spatially confined, making mmWave links more resilient to eavesdropping and jamming attacks. However, the mmWave radios locate each other and establish communication by exhaustively probing all possible angular directions, increasing the mmWave radios susceptibility to attacks. In this demonstration, we showcase a secure beam management solution where our mmWave radios apply an adaptive beam management procedure that avoids probing the directions of potential attackers. We employ a Reinforcement Learning agent to control the probing and dynamically restrict sweeps to a subset of beams in the mmWave radios' codebook to avoid the locations of potential attackers based on a proposed metric that quantifies the beam sweeping secrecy capacity over a pre-defined area.