A Federated Approach to Scalable and Trustworthy Financial Fraud Detection

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.