A SECURE AND SCALABLE AI–BLOCKCHAIN FRAMEWORK FOR RISK MITIGATION AND FRAUD DETECTION IN DIGITAL BANKING

Paper ID: EIJTEM_2025_12_4_50-58

Author's Name: Sita Rama Siddanthi Vudayamarri

Volume: 12

Issue: 4

Year: 2025

Page No: 50-58

Abstract:

The rapid digitization of the Banking, Financial Services, and Insurance (BFSI) sector driven by platforms such as UPI, digital wallets, and cross-border payment gateways has increased both the scale and sophistication of cyber fraud and financial threats. Traditional centralized security mechanisms are no longer sufficient to address modern, distributed, and adaptive attack vectors. To overcome these challenges, this paper proposes an AI–Blockchain-Driven Adaptive Cybersecurity Framework for Real-Time Fraud Detection in the BFSI Sector. The proposed architecture integrates Federated Learning (FL) to enable collaborative fraud detection across financial institutions without sharing sensitive customer data, and Blockchain to ensure tamper-proof logging, traceability, and trust in model updates and threat intelligence. The framework is structured into five layers: (i) Threat Data Acquisition, (ii) Federated AI Training, (iii) Blockchain Ledger, (iv) Consensus and Incentive, and (v) Threat Response and Trust Layer. Experimental evaluation using real-time payment and transaction datasets demonstrates improved fraud detection accuracy (95.7%), reduced false positives, and enhanced tamper detection compared to traditional systems. This approach not only strengthens financial cybersecurity but also supports regulatory compliance with RBI and FATF standards, enabling real-time threat mitigation and secure collaboration between banks, fintech platforms, and regulatory bodies.

Keywords: Artificial Intelligence (AI), Blockchain, Federated Learning, Cybersecurity, Intrusion Detection System (IDS), Threat Intelligence, Real-Time Threat Prediction, Tamper Detection, UPI Fraud Detection, Digital Banking.

References:

1. A survey of data mining and machine learning methods for cybersecurity intrusion detection. IEEE Communications Surveys & Tutorials, 2016.
2. Outside the closed world: On using machine learning for network intrusion detection. IEEE Symposium on Security and Privacy, 2010.
3. A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018.UNSW-NB15: A comprehensive dataset for network intrusion detection systems. IEEE MILCOM, 2015.
4. Deep learning approach for intrusion detection using RNN and CNN. IEEE Access, 2017.
5. A survey of AI techniques for cybersecurity. IEEE Communications Surveys & Tutorials, 2020.
6. Aashraya, A., and P. Munaswamy. "IoT based military robot using raspberry Pi3." Eur J Molecular Clin Med (2020).
7. Adversarial ML taxonomy and challenges. IEEE Transactions on Security and Privacy, 2018.
8. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 2019.
9. Federated intrusion detection for IoT security. IEEE Internet of Things Journal, 2022.
10. C. Vijaya Bhaskar and P. Munaswamy, "Low Power High Gain Fully Integrated CMOS Power Amplifier using Power Combining and Mode Locking Architecture," 2020 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, 2020, pp. 1233-1239, doi: 10.1109/ICCSP48568.2020.9182230.
11. Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 2020.
12. Blockchain technologies for cybersecurity and privacy. IEEE Access, 2020.
13. Blockchain-based decentralized security architecture. Future Generation Computer Systems, 2021.
14. Blockchain-enabled threat intelligence sharing. IEEE Transactions on Information Forensics and Security, 2022.
15. Hybrid blockchain–federated learning architecture for secure cybersecurity analytics. IEEE Access, 2023.

View PDF