EL-GNN: A Continual-Learning-Based Graph Neural Network for Task-Incremental Intrusion Detection Systems

Modern network infrastructures have significantly improved global connectivity while simultaneously escalating network security challenges as sophisticated cyberattacks increasingly target vital systems. Intrusion Detection Systems (IDSs) play a crucial role in identifying and mitigating these threats, and recent advances in machine-learning-based IDSs have shown promise in detecting evolving attack patterns. Notably, IDSs employing Graph Neural Networks (GNNs) have proven effective at modeling the dynamics of network traffic and internal interactions. However, these systems suffer from Catastrophic Forgetting (CF), where the incorporation of new attack patterns leads to the loss of previously acquired knowledge. This limits their adaptability and effectiveness in evolving network environments. In this study, we introduce the Elastic Graph Neural Network for Intrusion Detection Systems (EL-GNNs), a novel approach designed to enhance the continual learning (CL) capabilities of GNN-based IDSs. This approach enhances the performance of the GNN-based Intrusion Detection System (IDS) by significantly improving its capability to preserve previously learned knowledge from past cyber threats while simultaneously enabling it to effectively adapt and respond to newly emerging attack patterns in dynamic and evolving network environments. Experimental evaluations on trusted datasets across multiple task scenarios demonstrate that our method outperforms existing approaches in terms of accuracy and F1-score, effectively addressing CF and enhancing adaptability in detecting new network attacks.