Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE

2026-03-13

AI Summary

This work proposes a federated learning framework based on NVIDIA FLARE to enable efficient fraud detection across heterogeneous financial institutions under stringent privacy and data sovereignty constraints. By aggregating deep neural network models via Federated Averaging (FedAvg), integrating DP-SGD for differential privacy, and employing Shapley value-based interpretability analysis, the approach ensures regulatory compliance and model transparency without exchanging raw transaction data. The study presents the first empirical validation of federated anomaly detection on real-world, non-IID financial data, demonstrating that the federated model achieves an F1 score of 0.903—significantly outperforming local models (0.643) and closely approaching the performance of a centralized baseline (0.925)—while converging rapidly within ten communication rounds.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Fraud-related financial losses continue to rise, while regulatory, privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems. Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating federated anomaly detection for payment transactions using the NVIDIA FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via federated averaging (FedAvg), we demonstrate that federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10 federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential privacy via DP-SGD and demonstrate favorable privacy-utility trade-offs...

Problem

• Federated Learning
• Fraud Detection
• Privacy Preservation
• Non-IID Data
• Data Sovereignty

Innovation

• Federated Learning
• Fraud Detection
• Non-IID Data
• Differential Privacy
• Model Interpretability