Open access
2026
DMGCRL: Dynamic Multi-Scale Graph Contrastive Representation Learning for Network Intrusion Detection
Dynamic Multiscale Graph Contrastive Representation Learning (DMGCRL), a self-supervised framework that hierarchically models network intrusions at different levels, is proposed, which consistently outperforms SOTA methods in network intrusion detection.
Raeed Al-Sabri, Abdullatif Albaseer, Mohamed M. Abdallah et al.
· IEEE Transactions on Network... · 0 citations