A Comprehensive Review of Advanced Machine Learning Techniques for Enhancing Cybersecurity in Blockchain Networks
Keywords:
Blockchain Security, Machine Learning, Cybersecurity, Deep Learning, Federated Learning, Smart Contracts, Anomaly Detection, Decentralized Networks, Cyber Threats, AI in BlockchainAbstract
Blockchain technology has revolutionized digital transactions, offering decentralized, transparent, and immutable systems. However, as blockchain networks gain popularity, they face increasing cybersecurity threats, including Sybil attacks, 51% attacks, and smart contract vulnerabilities. Machine Learning (ML) has emerged as a potent tool to enhance security in blockchain by detecting anomalies, mitigating attacks, and strengthening authentication processes. This paper provides a comprehensive review of advanced ML techniques such as deep learning, reinforcement learning, federated learning, and adversarial networks applied to blockchain security. We evaluate the latest contributions in this domain, analyzing their effectiveness, challenges, and future prospects in the context of cybersecurity resilience. This review further explores how ML models can adapt to evolving cyber threats and maintain the integrity of decentralized networks.
References
Conti, M., Kumar, S., Lal, C., & Ruj, S. (2020). A survey on security and privacy issues of blockchain technology. Future Generation Computer Systems, 107, 921-953.
Feng, Q., He, D., Zeadally, S., Li, N., & Wang, H. (2021). A survey on privacy protection in blockchain system. Journal of Network and Computer Applications, 169, 102807.
Liu, Y., Lin, X., Shen, X., & Liang, X. (2022). Securing blockchain-based IoT with deep reinforcement learning. IEEE Internet of Things Journal, 9(3), 1785-1797.
Xu, Z., Wang, S., Wang, W., & Zhang, Y. (2023). Federated learning for blockchain security: A decentralized approach. IEEE Transactions on Information Forensics and Security, 18, 1052-1065.
Wang, Z., & Zhang, P. (2023). Adversarial machine learning attacks in blockchain-based AI systems. Computers & Security, 122, 103448.
Alharbi, F., Sidorov, M., & Yoo, P. (2020). Blockchain-based anomaly detection using machine learning. Security and Privacy, 3(2), e101.
Saad, M., Njilla, L., Kamhoua, C., & Kwiat, K. (2021). Countering blockchain adversarial attacks with AI-based security solutions. IEEE Transactions on Dependable and Secure Computing, 19(1), 150-163.
Zheng, Z., Xie, S., Dai, H., Chen, X., & Wang, H. (2020). An overview of blockchain security models. ACM Computing Surveys, 53(1), 1-32.
Salah, K., Rehman, M., & Dandan, S. (2022). Blockchain for AI security: Challenges and opportunities. Journal of Cybersecurity, 8(3), 1-15.
Li, H., Katos, V., & Patel, A. (2023). Blockchain threat detection using federated learning. IEEE Access, 11, 33465-33478.
Mahmud, R., Kotobi, K., & Buyya, R. (2021). Blockchain-enabled secure ML in edge computing. Future Generation Computer Systems, 115, 465-478.
Rahman, A., Shah, S. & Tariq, U. (2023). Federated deep learning for anomaly detection in smart contracts. Expert Systems with Applications, 213, 118915.
Zhang, Y., Li, P., & Chen, X. (2022). Reinforcement learning-based blockchain consensus mechanism for security enhancement. IEEE Transactions on Systems, Man, and Cybernetics, 52(4), 786-798.
Ahmed, K., & Khan, S. (2023). AI-driven security frameworks for blockchain networks. Cybersecurity Journal, 15(2), 45-62.
Bose, S., Gupta, S., & Li, F. (2021). Privacy-preserving blockchain security using machine learning. International Journal of Information Security, 20(6), 987-1002.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Mukesh V (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
