PoS-FedFraud: A Robust Proof-of-Stake Framework for Decentralized Financial Fraud Detection in Federated Learning

Abstract

Federated Learning (FL) enables collaborative model training across decentralized data silos without raw data exchange, making it particularly attractive for privacy-sensitive domains like financial fraud detection. However, FL introduces critical vulnerabilities, notably the poisoning of global models through malicious client updates. Traditional defense mechanisms often rely on computationally expensive aggregation rules or complex anomaly detection. This paper introduces PoSFedFraud, a robust framework that integrates a Proof-of-Stake (PoS) economic layer directly into the federated aggregation process for financial fraud detection. By combining staking mechanisms with a dynamic reputation system, PoS-FedFraud economically disincentivizes adversarial behavior through automatic slashing and trust decay. We simulate a toy fraud detection scenario using a 29-dimensional feature space, demonstrating how the framework defends against norm-based gradient poisoning attacks. Our experimental results show that PoS-FedFraud successfully identifies and penalizes malicious actors—reducing their stake and trust upon detection—while maintaining global model convergence. The proposed method offers an incentive-compatible punitive layer that complements existing robust aggregation and anomaly-detection techniques for decentralized financial applications.