A Critical Cloud Security Risks Detection Using Artificial Neural Networks at Banking Sector

This research uses Artificial Neural Network (ANN) algorithms to forecast cloud computing and security issues. To forecast cloud security level performance, suggested Levenberg–Marquardt dependent Back Propagation (LMDBP) Equations. The precision of cloud security level prediction-based could computing also be approximated using LMSBP techniques. Artificial neural networks (ANNs) are a more effective methodology to improve efficiency and learn neural membership functions. The cloud vector analysis has been used to collect data dynamically for risk detection. Based on their experience with cloud computing in the banking industry, 40 bankers’ data were selected from both inside and outside Malaysian banking organizations for this study. The LMBP, on the other hand, is a non-linear optimization model for calculating the performance of a prediction model by evaluating the Mean Square Error (MSE). The output is acceptable if the MSE is minimal, which is less than theshold value i.e 0.45. This research was carried out on cloud banking developers and IT administrators’ teams. The optimal integrating strategy with ANNs algorithms forecasts and minimizes important security and cloud issues. Optimistic predictions of significant cloud security problems, on the other hand, would increase the cloud-based banking performance. The performance measures like accuracy 98.76%, sensitivity 97.34%, Recall 94.53%, and F measure 97.82% had been attained. These results outperform the methodology and compete with current techniques.