A Trust Model for Multi-Hop 5G Networks: A Reinforcement Learning Approach

Abstract

Trust investigation in 5G the next-generation wireless network, is still naive. The article investigates into a trust model based on reinforcement learning (RL) to select a legitimate (or trusted) forwarding entity (or node). RL can be embedded in an entity (that can be legitimate or malicious) to enable to learn a higly dynamic and heterogenous environments. The legitimate entity (e.g., a node) uses RL to select the best possible next hop forwarder (a relay) and to successfully transmit the desired packet towards the destination while the malicious entities exist in the network. The malicious entity can also use RL to launch an attack (i.e., intelligent attack) without being detected. Simulation results show that the legitimate entity can learn fast (i.e., converge fast) at a higher learning rate (i.e., $\alpha=0.9$) and perform well in terms of trusted forwarder selection. Nevertheless, the malicious entity can also learn fast and launch successful attacks (i.e., affecting the throughput by dropping the packets) without being detected due to its fugitive nature.