Deep-Reinforcement-Learning-Based Intrusion Detection in Aerial Computing Networks
Jing Tao, Ting Han, Ruidong Li
Abstract
The proliferation of unmanned aerial vehicles (UAVs) leads to various applications in different fields. Due to the easy deployment and dynamic reconfigurability of UAVs, they can provide and support multiple services for users, such as surveillance, sensing, and logistics. However, the increasing attention to UAV applications exposes it to security threats. The openness and multi-connectivity characteristics make UAV networks more vulnerable to malicious attacks. In this article, to protect the security of UAV networks, we present a deep reinforcement learning approach to detect malicious attacks in UAV aerial computing networks. We first provide the framework of UAV aerial computing networks and potential applications. Intrusion threats in UAV aerial computing networks are then discussed. Next, we present a case study of deep-reinforcement-learning-em-powered intrusion detection to protect the security services. Finally, we present the conclusion and several promising research directions.