GraphMatch: A Graph-Based Trust-Aware Framework for Secure Multi-Objective Task Scheduling in Heterogeneous Edge Computing

With the rapid development of IoT and 5G technologies, edge computing has become a critical infrastructure for intelligent applications. However, the openness and heterogeneity of edge computing environments pose severe security challenges: malicious edge nodes may steal sensitive data or tamper with computation results. Existing task scheduling algorithms primarily focus on performance optimization, lacking comprehensive consideration of security and trust. To address these challenges, this paper proposes GraphMatch, a security-aware task scheduling framework based on Graph Convolutional Network (GCN). GraphMatch models task scheduling as a constrained graph matching problem and achieves multi-objective optimization of security, trust, and performance through four synergistic modules: (1) Multi-hop Trust Propagation that expands trust coverage by discovering indirect trust paths; (2) Trust-Guided GCN that learns optimal task-device matching by fusing five scoring mechanisms; (3) NSGA-III-based Multi-objective Optimization that explores Pareto optimal solutions among makespan, trust, and security objectives; (4) Laplacian Load Balancing that achieves workload distribution through spectral graph diffusion. Experimental results demonstrate that GraphMatch achieves a trust score of 0.8869, representing a 10.0% improvement over the state-of-the-art SecDS algorithm. GraphMatch attains 100% malicious device avoidance rate and sensitive task protection rate while maintaining competitive makespan performance. Scalability experiments verify the algorithm's stability across 50-250 device scales, and robustness experiments confirm its reliability under 5%-30% malicious node ratios. GraphMatch provides an effective solution for security-sensitive task scheduling in edge computing.