FraudGuard-BC: A Hybrid AI-Blockchain Framework for Real-Time Financial and Cryptocurrency Fraud Detection

Author

Dr. K. R. Martin, Reema Jasmine M

Abstract

 Financial and cryptocurrency fraud has grown in scale and sophistication, yet most existing defences remain single-plane: pure blockchain ledgers verify authenticity but cannot reason about behavioural intent, while pure AI models flag anomalies without an immutable audit trail. Prior work has advanced each plane in isolation — blockchain-only check-authentication schemes, blockchain-based federated learning (BCFL) surveys, and AI-blockchain-cybersecurity synergy frameworks restricted to a single BFSI market — but no unified, platform-agnostic pipeline has been validated across both public (Bitcoin, Ethereum) and permissioned (Hyperledger) chains. This paper reviews the existing consensus algorithms and anomaly-detection taxonomies that underpin these platforms and proposes FraudGuard-BC, a five-layer framework that couples a machine-learning anomaly-detection layer (Random Forest, XGBoost, LSTM) with platform-native ledger verification (PoW, PoS, PBFT/Raft), a cybersecurity log-correlation layer, and a real-time early-warning layer, all converging on a single decision-and-commit stage. The proposed methodology is described step-by-step, evaluated conceptually against the reviewed baselines, and benchmarked on public datasets and simulated permissioned-ledger logs. The paper concludes that the synergy design generalises across consensus models better than any single-plane approach, and outlines future work on federated cross-institution training and post-quantum-safe ledger verification.

Keywords

blockchain, artificial intelligence, fraud detection, anomaly detection, Proof of Work, Proof of Stake, PBFT, Hyperledger Fabric, federated learning, cybersecurity

Full Text:

Download Paper PDF

References

[1] J. Krishna Priya, M. Reema Jasmine, and M. Deepika, "A Comparative Study of Bitcoin & Hyperledger as Blockchain Platforms," PG Dept. of Computer Applications, Holy Cross College (Autonomous), Trichirapalli, India, 2024.

[2] B. Hammi, S. Zeadally, Y. C. E. Adja, M. Del Giudice, and J. Nebhen, "Blockchain-Based Solution for Detecting and Preventing Fake Check Scams," IEEE Trans. Eng. Manag., vol. 69, no. 6, pp. 3710-3725, 2022.

[3] A. A. Ahmed and O. O. Alabi, "Secure and Scalable Blockchain-Based Federated Learning for Cryptocurrency Fraud Detection: A Systematic Review," IEEE Access, vol. 12, pp. 102219-102241, 2024.

[4] B. Fetaji, M. Fetaji, A. Hasan, S. Rexhepi, and G. Armenski, "FRAUD-X: An Integrated AI, Blockchain, and Cybersecurity Framework With Early Warning Systems for Mitigating Online Financial Fraud: A Case Study From North Macedonia," IEEE Access, vol. 13, pp. 48068-48082, 2025.

[5] M. U. Hassan, M. H. Rehmani, and J. Chen, "Anomaly Detection in Blockchain Networks: A Comprehensive Survey," IEEE Commun. Surveys Tuts., 2022.

[6] S. Nakamoto, "Bitcoin: A Peer-to-Peer Electronic Cash System," Cryptography Mailing List, 2008.

[7] E. Androulaki et al., "Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains," in Proc. 13th EuroSys Conf., 2018, art. no. 30.

[8] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, "Communication-Efficient Learning of Deep Networks from Decentralized Data," in Proc. 20th Int. Conf. Artif. Intell. Statist. (AISTATS), PMLR, 2017, pp. 1273-1282.

[9] Z. Zheng, S. Xie, H.-N. Dai, X. Chen, and H. Wang, "Blockchain Challenges and Opportunities: A Survey," Int. J. Web and Grid Services, vol. 14, no. 4, pp. 352-375, 2018.

[10] Y. Alghofaili, A. Albattah, and M. A. Rassam, "A Financial Fraud Detection Model Based on LSTM Deep Learning Technique," J. Appl. Secur. Res., vol. 15, no. 4, pp. 498-516, 2020.

[11] W. Hilal, S. A. Gadsden, and J. Yawney, "Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances," Expert Syst. Appl., vol. 193, art. no. 116429, 2022.

[12] V. M. Gaikwad, K. Meher, R. Dass, A. S. Jonista, J. D'Souza, and R. Victor, "Fraud Detection Using Machine Learning and Blockchain," Int. J. Recent Innov. Trends Comput. Commun., vol. 11, no. 5, pp. 45-50, 2023.

[13] H. Kanezashi, T. Suzumura, X. Liu, and T. Hirofuchi, "Ethereum Fraud Detection with Heterogeneous Graph Neural Networks," arXiv preprint arXiv:2203.12363, 2022.

[14] A. Xiong, Y. Tong, C. Jiang, S. Guo, S. Shao, J. Huang, W. Wang, and B. Qi, "Ethereum Phishing Detection Based on Graph Neural Networks," IET Blockchain, vol. 4, no. 3, pp. 226-234, 2024.

[15] P. Li, Y. Xie, X. Xu, J. Zhou, and Q. Xuan, "Phishing Fraud Detection on Ethereum Using Graph Neural Network," in Proc. Int. Conf. Blockchain and Trustworthy Systems (BlockSys), Springer, 2022, pp. 362-375.

[16] S. Li, G. Gou, C. Liu, C. Hou, Z. Li, and G. Xiong, "TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection," arXiv preprint arXiv:2204.13442, 2022.

[17] Z. Chen, S.-Z. Liu, J. Huang, Y.-H. Xiu, H. Zhang, and H.-X. Long, "Ethereum Phishing Scam Detection Based on Data Augmentation Method and Hybrid Graph Neural Network Model," Sensors, vol. 24, no. 12, art. no. 4022, 2024.

[18] S. Li, F. Xu, R. Wang, and S. Zhong, "Self-Supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection," arXiv preprint arXiv:2106.10176, 2021.

[19] H. Rabbani, M. F. Shahid, T. J. S. Khanzada, S. Siddiqui, M. M. Jamjoom, R. B. Ashari, Z. Ullah, M. U. Mukati, and M. Nooruddin, "Enhancing Security in Financial Transactions: A Novel Blockchain-Based Federated Learning Framework for Detecting Counterfeit Data in Fintech," PeerJ Comput. Sci., vol. 10, art. no. e2280, 2024.

[20] N. Innan, A. Sawaika, A. Dhor, S. Dutta, S. Thota, H. Gokal, and M. Bennai, "Financial Fraud Detection Using Quantum Graph Neural Networks," Quantum Mach. Intell., vol. 6, 2024.

[21] T. Awosika, R. M. Shukla, and B. Pranggono, "Transparency and Privacy: The Role of Explainable AI and Federated Learning in Financial Fraud Detection," IEEE Access, vol. 12, pp. 64551-64560, 2024.

[22] M. Abdul Salam, K. M. Fouad, and D. L. Elbably, "Federated Learning Model for Credit Card Fraud Detection With Data Balancing Techniques," Neural Comput. Appl., vol. 36, pp. 6231-6256, 2024.

 

 

 

Share your valuable work from Social Media Buttons