A Robust Bayesian Dynamic Stackelberg Game Theory Detection Scheme for Man-in-the-Middle Attack in Mobile Edge Computing Networks

Abstract

Mobile Edge Computing (MEC) networks are emerging technologies transforming how data is processed, stored, and delivered at the edge network, enhancing performance and reducing latency. However, the technology introduces significant cybersecurity challenges, specifically Man-in-the-Middle (MitM) attacks. These attacks compromise sensitive data and can disrupt normal services. This study proposes a robust detection scheme based on Bayesian Dynamic Stackelberg Game Theory to address these vulnerabilities. By incorporating Bayesian inference, the scheme considers uncertainties in the attacker’s behaviour and the network environment, enabling the defender to update its strategies dynamically based on observed actions. The simulation results show that the proposed scheme significantly improves the detection scheme for MitM attacks in MEC networks, outperforming other schemes considered in the study. The findings show that integrating Game Theory with Bayesian analysis provides a promising approach for developing adaptive and resilient cybersecurity strategies in the evolving landscape of edge computing.