A Cross-Institutional Financial Fraud Collaborative Detection Algorithm Based on FedGAT Federated Graph Attention Network
Open Access
Abstract
Cross-institutional collaborative fraud detection is essential for combating increasingly sophisticated financial fraud, yet privacy regulations and data silos severely constrain knowledge sharing among institutions. This study aims to develop a privacy-preserving framework that enables effective collaborative fraud detection while protecting raw data, with particular emphasis on exploiting symmetry properties in federated architectures and graph topology analysis. We propose an Adaptive Federated Graph Attention Network (FedGAT), which employs spatio-temporal graph attention mechanisms to capture topological structures and dynamic fraud patterns within institutional transaction networks. The framework introduces a symmetric similarity matrix derived from graph topological features, where the symmetry property () ensures consistent and unbiased measurement of structural relationships between any pair of institutions. Based on this symmetric similarity metric, an adaptive weighted aggregation mechanism is designed for cross-institutional parameter fusion, enabling balanced knowledge transfer that respects the symmetric collaborative relationship among participating institutions. The symmetric information exchange protocol between local institutions and the central server further guarantees equitable contribution and benefit distribution throughout the federated learning process. The framework is evaluated on the Elliptic Bitcoin transaction dataset and the IEEE-CIS fraud detection dataset, with recall rate and false positive rate as primary performance metrics. Results show that FedGAT achieves a recall of 0.85 and a false-positive rate of 0.038 in single-institution detection, representing approximately 40% and 70% improvements over existing methods, respectively. In collaborative detection across five virtual institutions, the symmetry-aware adaptive aggregation mechanism enables all participants to achieve performance gains exceeding 15% while completely eliminating negative transfer effects observed in simple averaging approaches. This work contributes a novel symmetry-based federated learning framework that balances privacy protection with detection performance, advancing the literature on cross-institutional financial risk management.
Keywords
Funding Information
- Asian Business Research Institute (ABRI-2025ZD042801)
- China Business Accounting Institute (2025zsx031)
This publication has 31 references indexed in Scilit:
- Finding a needle in a haystack: A machine learning framework for anomaly detection in payment systemsThe Journal of Finance and Data Science, 2025
- Detecting financial fraud risk using machine learning: Evidence based on different categories and matching samplesFinance Research Letters, 2025
- Temporal transaction network anomaly detection for Industrial Internet of Things with federated graph neural networksComputers & Industrial Engineering, 2025
- Advancing financial risk management: A transparent framework for effective fraud detectionFinance Research Letters, 2025
- Multi‐Distance Spatial‐Temporal Graph Neural Network for Anomaly Detection in Blockchain TransactionsAdvanced Intelligent Systems, 2025
- Multimodal federated learning: Concept, methods, applications and future directionsInformation Fusion, 2024
- An overview of implementing security and privacy in federated learningArtificial Intelligence Review, 2024
- A survey on privacy-preserving control and filtering of networked control systemsInternational Journal of Systems Science, 2024
- COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic ForecastingInformation Fusion, 2024
- Financial fraud detection using quantum graph neural networksQuantum Machine Intelligence, 2024