A Trusted Hybrid Learning Approach to Secure Edge Computing

Securing edge computing has drawn much attention due to the vital role of in Fifth Generation (5G) wireless networks. Artificial Intelligence (AI) been adopted protect networks against attackers targeting connected devices or channel. However, proposed detection mechanisms could generate a high false rate, especially unknown attacks defined as zero-day threats. Thereby, we propose and conceive new hybrid learning security framework that combines expertise experts strength machine network from known attacks, while minimizing rate. Moreover, further decrease number detections, cyber mechanism based on Stackelberg game is used by engine (activated at each server) assess decisions provided neighboring engines.