• Proposes FedSTGCN, a novel framework integrating spatiotemporal graph neural networks (STGNNs) with federated learning for IoT intrusion detection.
• Enables collaborative model training across distributed IoT devices without sharing raw data, effectively addressing data privacy concerns.
• Achieves over 97% accuracy in binary classification and over 92% weighted F1-score in multiclass classification, outperforming existing methods.
• Validates the approach on two widely used IoT intrusion detection datasets, demonstrating robust performance and practical applicability.