Nowadays, securely sharing medical data is one of the significant concerns in blockchain technology. The existing blockchain approaches have faced high time consumption, low confidentiality, and high memory usage for transferring the file in a secure way because of attack harmfulness and large unstructured records. It has ended in security threat, so the integrity of the user data has been lost. Hence, a novel hybrid Deep Belief-based Diffie Hellman (DBDH) security framework was presented to protect medical data from malicious events. Incorporating a deep belief neural system continuously monitors the system and identifies the attacks. Initially, the IoMT dataset was collected from the standard site and imported into the system. Moreover, hash 1 was calculated for the original data and stored in the cloud server for verification. Then, the original data was encrypted with a private key for data hiding. The incorporation of homomorphic property helps to calculate hash 2 for encrypted data. Finally, in the verification module, both hash values are verified. In addition, cryptanalysis was performed by launching an attack to validate the performance of the designed model. Moreover, the estimated outcomes of the presented model were compared with existing approaches to determine the improvement score.

No abstract