Secure Federated Cloud Storage Protection Strategy Using Hybrid Heuristic Attribute-Based Encryption With Permissioned Blockchain

Abstract

The rapid growth of the Internet of Medical Things (IoMT) has introduced significant security and privacy challenges in managing and protecting medical data. This paper proposes a secure federated cloud storage system designed to address these challenges using a hybrid heuristic attribute-based encryption (ABE) scheme integrated with a permissioned Blockchain. The proposed system enhances data confidentiality and integrity by first collecting medical information and then encrypting it with ABE using an optimal key generated by the Hybrid Mexican Axolotl with Energy Valley Optimizer (HMO-EVO). The encrypted data is securely stored in a permissioned blockchain, ensuring robust access control and protection against data breaches. For effective healthcare monitoring, the system employs federated learning with a Multi-scale Bi-Long Short-Term Memory and Gated Recurrent Unit (MBiLSTM-GRU) to predict diseases accurately. This federated approach allows for decentralized training of deep learning models, preserving patient data privacy while leveraging collective learning. Experimental results show that the proposed system outperforms conventional methods in terms of security, efficiency, and predictive accuracy. This research offers a comprehensive framework for secure medical data management, combining the strengths of federated learning and blockchain technology to address the critical issues of data ownership, regulatory compliance, and privacy in IoMT networks.