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

TL;DR

This paper demonstrates that federated learning can effectively detect payment fraud across multiple institutions, achieving high accuracy while preserving data privacy and regulatory compliance, and is practical for real-world financial environments.

Contribution

It provides a comprehensive industry-oriented evaluation of federated anomaly detection for payment fraud, validating its effectiveness on non-IID data and integrating privacy-preserving techniques.

Findings

Federated models achieve a mean F1-score of 0.903, close to centralized training.

Strong performance within 10 federated communication rounds.

Federated models rely on domain-relevant decision signals and support differential privacy.

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...