Enhancing Cybersecurity and Secure Data Transmission in Cloud Computing Using Graph Neural Network Models

Cloud computing has transformed data storage and administration, enabling users to access and save data online. Nonetheless, guaranteeing secure data transformation continues to be a significant cybersecurity concern, especially regarding the safe transmission of data within cloud systems. Conventional networks convey data via the most direct route between nodes, which may not ensure security. Customers encounter difficulties with cloud security and access control, notwithstanding the pay-as-you-go service model. The proposed system incorporates preprocessing and normalization modules to improve data security. Feature selection is enhanced through the utilization of GA, together with Mutation and Crossover procedures. GNN are utilized to efficiently depict dependencies between roles using graphical representations of neural networks. Experimental findings indicate the superiority of this method, with an average accuracy of 99.48% and an F1-score of 99.57% across all datasets. The performance research demonstrates that the GNN model much surpasses current security techniques, hence enhancing cybersecurity and facilitating secure data transformation. This study underscores the significance of sophisticated security frameworks in tackling emerging cloud security issues and accentuates the contribution of intelligent models in augmenting data protection.