FedQ-Fraud: A Quantum-Enforced Federated Learning Framework for Financial Fraud Detection

The rapid growth of online financial transactions has made fraud detection a critical priority, especially with evolving fraud strategies that evade traditional systems. This paper presents a novel and secure fraud detection framework integrating Deep Learning (DL), Federated Learning (FL), and Quantum Encryption Communication (QEC). Our approach ensures high fraud detection accuracy while maintaining user data privacy and secure communication. We implemented a 3-layer GRU model using the MOON algorithm under the FL paradigm and achieved a global accuracy of 97.47%, outperforming traditional models like LSTM, 1D-CNN and XGBoost. To secure model parameter exchange between clients and server, we evaluated two entanglement-based Quantum Key Distribution (QKD) protocols - BBM92 and MDI-QKD. Experimental results revealed BBM92 to be more stable and suitable for integration with FL, demonstrating superior average secret key rate (SKR) and lower quantum bit error rate (QBER). The proposed system effectively combines accuracy, privacy, and quantum security, making it a scalable solution for real-world fraud detection.