SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation

ArXi:2605.18913v1 Announce Type: cross The U. S. financial system processes approximately 1.3M interbank transactions daily, yet no system in the reviewed literature models fraud propagation across the interbank network using fraud co-occurrence edge features. Prior interbank GNN architectures model credit contagion using credit distress supervision signals, producing systems misaligned for fraud forensics.