A Hybrid Approach to Fraud Detection: Integrating Explainable Deep Learning with Blockchain-Based Identity Verification

Abstract

Modern online finance operations create difficult obstacles for detecting fraudulent activity. While deep learning (DL) models effectively identify fraudulent activities, their "black-box" nature raises concerns about trust and interpretability. The research design recommends an XDL-Blockchain solution for fraud detection that enhances transparency and accuracy alongside enhanced security capabilities. SHAP and Grad-CAM methods supply interpretation features that enhance stakeholder confidence and blockchain technologies deliver permanent decentralized identity proofing systems which minimize fraudulent activity. Experimental assessments using genuine financial data show that the proposed model delivers superior outcomes compared to conventional detection systems regarding precision and network security. The framework unites artificial intelligence with blockchain technology to provide banks with a dependable system that delivers reliable detection of contemporary financial fraud.