XGA-E: an explainability-enhanced graph neural network for network traffic anomaly detection

Today's article comes from the journal of Cybersecurity. The authors are Yang et al., from Leshan Normal University, in China. In this paper, they're proposing a new system for network-traffic anomaly detection. It's a multi-stage pipeline that starts with a graph neural network (GNN), then adds classifiers and an explainability tool.

DOI: 10.1186/s42400-025-00487-x