ORCID

Abstract

Financial fraud remains a critical challenge for digital banking, requiring detection solutions that ensure both scalability and data privacy. Traditional centralized approaches face limitations due to security risks and system bottlenecks. This paper proposes FedFraud, a novel federated learning (FL) framework that detects fraudulent transactions without sharing raw data. FedFraud introduces two key innovations: (i) a trust-aware client aggregation mechanism that assigns weights based on update reliability and (ii) an asynchronous communication protocol enabling clients to contribute updates independently. Evaluated on the Credit Card Fraud Detection dataset under a nonidentically distributed (non-IID) data setting where client data distributions differ significantly, FedFraud achieves an F1-score of 0.90 and area under the ROC curve (AUC) of 0.96, outperforming FedAvg and state-of-the-art methods like FedGAT and FL-BGAT. It also reduces privacy leakage to 1.5% and limits gradient reconstruction success—the ability to infer raw data from model updates to 15%, compared to 35% for FedAvg. Designed for real-world deployments such as cross-institutional banking systems, FedFraud enables scalable, robust, and privacy-preserving fraud detection across distributed financial networks.

Publication Date

2025-09-12

Publication Title

SECURITY AND PRIVACY

Volume

8

Issue

5

ISSN

2475-6725

Acceptance Date

2025-08-27

Deposit Date

2025-12-10

Funding

The paper was funded by the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, Saudi Arabia, and the authors gratefully acknowledge DSR for its technical and financial support as well as the University of Plymouth for providing research support that significantly contributed to the development of this work.

Keywords

asynchronous training, federated learning, fraud detection, privacy preservation, trusted aggregation

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS