Affiliation:
1. School of Computer Sciences and Engineering, Sandip University, India
2. Sandip University, India
Abstract
The increasing concerns over data breaches and privacy invasions highlight the critical need for enhanced privacy protections in the digital world. Since traditional privacy management techniques are rigid and cannot easily adjust to changing cyber threats, they frequently fail to meet these difficulties. The fusion of Blockchain and Technologies such as Federated Learning (FL) has come to light as a viable means of guaranteeing secure, open, and confidential interactions. While the individual merits of Blockchain in ensuring data integrity and FL in deriving insights are well-established, their synergistic effects particularly in the era of privacy preservation are yet to be fully explored. This fusion has the potential to revolutionize sectors like healthcare, finance, and supply chain by offering unprecedented levels of data privacy without compromising on system performance. This research described a review of existing models that employ machine learning techniques for privacy preservation operations within blockchain frameworks. Utilizing a set of predetermined metrics delay, throughput, energy efficiency, privacy levels, deployment cost, and scalability the paper compares these models to provide a nuanced understanding of their capabilities and limitations. Our in-depth comparison elucidates the trade-offs involved in selecting specific blockchain-ML models for diverse applications.
Reference58 articles.
1. How to backdoor federated learning.;E.Bagdasaryan;Proceedings of the International Conference on Artificial Intelligence and Statistics,2020
2. Analyzing federated learning through an adversarial lens.;A. N.Bhagoji;Proceedings of the International Conference on Machine Learning,2019
3. Sharemind: A Framework for Fast Privacy-Preserving Computations
4. A Sharding Scheme-Based Many-Objective Optimization Algorithm for Enhancing Security in Blockchain-Enabled Industrial Internet of Things
5. A many-objective optimization recommendation algorithm based on knowledge mining