A Blockchain-Integrated Computational Framework for Secure Multi-Party Machine Learning in Cloud-Edge Collaboration
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V1I1P101Keywords:
Blockchain, Multi-Party Machine Learning (MPML), Cloud-Edge Collaboration, Federated Learning, Secure Multi-Party Computation (SMPC), Data Privacy, Model IntegrityAbstract
The swift cloud and edge computing development promoted the implementation of distributed learning models as different organizations can train them cooperatively and share sensitive data without the need to access it. There is however a serious challenge of making sure that the data privacy, model integrity and secure collaboration is ensured. The paper introduces a blockchain-enhanced framework to conduct computations based on secure multi-party machine learning (MPML) over cloud-edge collaborative settings. The framework proposed uses blockchain technology to build a sense of trust, immutability and verifiability during data sharing as well as training the model. The framework also includes the principles of secure multi-party computation (SMPC) and federation of learning, designed to maintain the privacy of data, but to make models optimize the performance on a heterogeneous set of nodes. We also give a step by step methodology of the system architecture, consensus protocols, encryption mechanisms, and collaborative learning algorithms. Experimental testing illustrates the effectiveness of the framework in regard to security, scale, and the accuracy of the model. Indeed, our findings reveal that blockchain coupled with MPML will help to solve security threats, accountability, and trust among cooperating entities substantially. The framework offers the solid solution to the real-world cloud-edge collaborative applications, such as healthcare, finance, and smart cities
References
[1] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 3(5), 637–646.
[2] Satyanarayanan, M. (2017). The Emergence of Edge Computing. Computer, 50(1), 30–39.
[3] Wang, S., Zhang, X., Zhang, Y., Wang, L., Yang, J., & Wang, W. (2017). A Survey on Mobile Edge Networks: Convergence of Computing, Caching and Communications. IEEE Access, 5, 6757–6779.
[4] Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2017). Convergence of Edge Computing and Deep Learning: A Comprehensive Survey. IEEE Communications Surveys & Tutorials, 22(2), 869–904.
[5] Li, E., Zhou, Z., & Chen, X. (2018). Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy. Proceedings of ACM HotEdge, 2018.
[6] McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. AISTATS 2017.
[7] Bonawitz, K., et al. (2017). Practical Secure Aggregation for Privacy-Preserving Machine Learning. ACM CCS 2017.
[8] Konečný, J., McMahan, B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated Learning: Strategies for Improving Communication Efficiency. arXiv:1610.05492.
[9] Smith, V., Chiang, C.-K., Sanjabi, M., & Talwalkar, A. (2017). Federated Multi-Task Learning. NeurIPS 2017.
[10] Shokri, R. & Shmatikov, V. (2015). Privacy-Preserving Deep Learning. CCS 2015.
[11] Christidis, K., & Devetsikiotis, M. (2016). Blockchains and Smart Contracts for the Internet of Things. IEEE Access, 4, 2292–2303.
[12] Zyskind, G., Nathan, O., & Pentland, A. (2015). Decentralizing Privacy: Using Blockchain to Protect Personal Data. IEEE Security and Privacy Workshops (SPW), 180–184.
[13] Swan, M. (2015). Blockchain: Blueprint for a New Economy. O’Reilly Media.
[14] Dorri, A., Kanhere, S. S., Jurdak, R., & Gauravaram, P. (2017). Blockchain for IoT Security and Privacy: The Case Study of a Smart Home. IEEE PerCom Workshops 2017.
[15] Kaur, K., Garg, S., & Buyya, R. (2018). Security and Privacy Challenges in Cloud-Edge Collaboration. IEEE Cloud Computing, 5(3), 64–72.
[16] Mohassel, Payman & Zhang, Yupeng. “SecureML: A System for Scalable Privacy-Preserving Machine Learning.” (2017)
[17] SecureML: A System for Scalable Privacy Preserving Machine Learning — Payman Mohassel & Yupeng Zhang, 2017.
[18] Takada, Toshiyuki; Hanada, Hiroyuki; Yamada, Yoshiji; Sakuma, Jun; &-others. “Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization.” (2016)
[19] Garg, Sanjam; Miao, Peihan; Srinivasan, Akshayaram. “Two-Round Multiparty Secure Computation Minimizing Public Key Operations.” (2018)
[20] (Survey) “An Exhaustive Survey on Privacy Preserving Machine Learning using Homomorphic Encryption and Secure Multiparty Computation Techniques.” (2017) — provides background though full details span beyond 2017.
