SCAFDS applies edge-feature graph attention on fraud co-occurrence metrics to detect interbank fraud and generate attribution-grounded SAR reports, reporting AUPRC 0.515 and AUROC 0.802 on IEEE-CIS data with gains over GraphSAGE-AML.
IEEE-CIS Fraud Detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCAFDS: Edge-Feature Graph Attention for Interbank Fraud Detection with Attribution-Grounded SAR Generation
SCAFDS applies edge-feature graph attention on fraud co-occurrence metrics to detect interbank fraud and generate attribution-grounded SAR reports, reporting AUPRC 0.515 and AUROC 0.802 on IEEE-CIS data with gains over GraphSAGE-AML.