Open access
Aug 2026
An Explainable and Interpretable GNN Based on Temporal Time Series: An IDS Approach
This work develops and compares traditional classifiers against a GNN-based IDS on the UNSW-NB15 dataset, for both binary and multiclass classification and reveals attack-specific structural patterns, confirming that temporally structured GNNs improve detection while providing interpretable predictions.
Alberto Caballero Ferrero, Shadi Motaali, Xavier Larriva-Novo et al.
· Electronics · 0 citations