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

2026-05-17

AI Summary

This study addresses the limitations of existing inter-bank anti-fraud systems in modeling fraud co-occurrence relationships and the lack of traceability in Suspicious Activity Reports (SARs), which hinders regulatory auditing. To overcome these challenges, the authors propose a seven-stage integrated monitoring pipeline that introduces fraud co-occurrence frequency as an edge feature to construct an inter-bank topological graph. The framework combines Graph Attention Networks with a bilinear risk fusion mechanism for systematic fraud detection and employs attribution-conditioned text generation to ensure each SAR is traceable to specific model outputs. Furthermore, it supports regulator feedback-driven adaptive updates of the graph topology. Evaluated on the IEEE-CIS dataset, the method achieves an AUPRC of 0.515 ± 0.032 and AUROC of 0.802 ± 0.018, significantly outperforming GraphSAGE-AML, and demonstrates consistent risk ranking against 4,279 FDIC enforcement records.

Abstract

The U.S. financial system processes approximately 1.3 million 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. No existing system generates SAR narratives with per-assertion forensic traceability to specific numerical detection outputs, creating regulatory auditability gaps in FinCEN-submitted reports. This paper introduces SCAFDS (Systemic Contagion-Aware Fraud Detection System), a seven-stage integrated surveillance pipeline addressing five structural limitations of prior art: (1) fraud-specific interbank topology encoding using fraud co-occurrence frequency metrics f(u,v,t) derived from FinCEN SAR registry records; (2) edge-feature-informed graph attention where coefficients are computed from both node representations and fraud co-occurrence edge features; (3) bilinear fraud co-occurrence risk fusion producing institution-level systemic fraud risk scores; (4) attribution-conditioned SAR narrative generation with per-assertion significance thresholds ensuring each FinCEN SAR assertion is traceable to a specific numerical pipeline output; and (5) topology-aware adaptive forensic feedback updating graph attention weights from regulatory dispositions. Experiments on the IEEE-CIS Fraud Detection Dataset (590,540 transactions) and a synthetic FDIC-aligned interbank network (8,103 institutions, 169,800 edges) show SCAFDS achieves AUPRC=0.515+/-0.032 and AUROC=0.802+/-0.018, representing +15.9pp and +13.7pp improvements over GraphSAGE-AML. Partial validation on FDIC enforcement action records (n=4,279) confirms consistent model ranking. USPTO Provisional Patent Application No. 64/061,083, filed May 8, 2026.

Problem

• interbank fraud detection
• fraud propagation
• SAR generation
• regulatory auditability
• graph attention

Innovation

• edge-feature graph attention
• fraud co-occurrence
• attribution-grounded SAR generation
• systemic fraud detection
• topology-aware feedback