Timestamp-Aware Spatio-Temporal Graph Contrastive Learning for Network Intrusion Detection
Researchers have developed a novel self-supervised Graph Neural Network (GNN) framework for network intrusion detection systems (NIDS). This approach explicitly utilizes real timestamps to capture temporal dependencies, addressing limitations in existing GNN-based NIDS that often treat traffic flows as temporally independent. The framework employs an E-GraphSAGE and LSTM encoder to extract spatial and temporal information, combined with a multi-view graph contrastive learning scheme for enhanced generalization and robustness. Experiments on four datasets demonstrate that this method significantly outperforms other self-supervised approaches and rivals supervised state-of-the-art GNN methods in performance while maintaining computational efficiency. AI