Real-Time Intelligent Detection of APT Attacks Using Mobile Edge Networks

Abstract

Advanced Persistent Threat (APT) attacks pose severe security risks to mobile edge networks due to their stealthy, long-term, and multi-stage nature. This paper proposes MERA-RD, a novel real-time APT detection framework that integrates multi-source data fusion, a Spatio-Temporal Graph Neural Network (ST-GNN) for temporal–spatial correlation modeling, and a Deep Q-Network (DQN)-based adaptive threshold adjustment mechanism. The framework is designed to address the challenges of heterogeneous device environments, dynamic traffic patterns, and stringent latency constraints in Mobile Edge Computing scenarios. Experimental evaluations in both simulated and real-world environments demonstrate that MERA-RD achieves high detection accuracy with low latency, validating its potential for practical deployment. The proposed approach provides a promising solution for enhancing the security of edge-based intelligent systems in the era of 6G networks.