An intelligent homomorphic blockchain approach for securing stock market data

Blockchain technology has been widely used in different sectors to secure data from malicious events. However, the traditional blockchain approach faces time consumption, security, and privacy challenges. Thus, a novel hybrid Recurrent Neural Diffie–Hellman was presented in this article. The presented model includes monitoring and verification modules. The monitoring module analyzes the dataset and neglects its malicious events. Further, hashing function was performed and stored in the cloud server. Consequently, crypto analysis was done to protect the data from attacks. Here, the homomorphism property was incorporated to improve the data integrity with hash verification. Furthermore, the robustness of the presented model was checked by launching Denial of Service and Brute Force attacks. The presented model was designed and validated in the python software with the stock market dataset. Finally, the developed model's performances are estimated and validated with a comparative analysis. The comparative analysis proves that the designed model provides better security to the system.