Strong authentication framework using statistical approach for cloud environments

Security is one of the important challenges faced by cloud computing. There are so many methods like encryption, firewall, and providing access control to achieve security. These methods alone cannot provide a flawless access to the available resources. We are in need of a paradigm that permits only authenticated users to access the resources from the cloud. The objective of the proposed paradigm is to provide a strong authentication. Our proposed method considers only the appropriate parameters from the available plenty of parameters, which is used to prove a user to be an authenticated person. The selection of the required parameters is achieved using Principle Component Analysis, then Support Vector Machine classifies accurately the authenticated and unauthenticated users. The simulation result shows that our proposed paradigm achieves high security. We compute our paradigm with various evaluation metrics and we compared with similar models like Support Vector Machine and Artificial Neural Networks. We got great improvement. In order to reduce the complexity, the number of parameters is reduced because, if the parameters are huge, the algorithm prediction will be more complex, which leads to false negatives.