• Proposes CRGT-SA, a hybrid deep learning model integrating CNN, LSTM, gated TCN, and self-attention for network intrusion detection.
• Achieves state-of-the-art performance with 91.5% binary and 90.5% multi-class accuracy on the UNSW-NB15 dataset, outperforming traditional and deep learning baselines.
• Demonstrates strong generalization ability through additional validation on the NSL-KDD dataset.
• Overcomes limitations of shallow machine learning by automatically extracting spatiotemporal features and selecting significant attributes via self-attention.