Cloud computing security assurance modelling through risk analysis using machine learning

The concept of Cloud Computing has exploded in popularity, and the reason for this is the cost-effective transmission, storage, and powerful computation it offers. The objective is to provide end-users with remote storage and data analysis capabilities using shared computing resources, lowering an individual’s total cost. Consumers, on the other hand, are still hesitant to use this technology due to security and privacy concerns. In this work a thorough overview of the various Cloud attacks and security challenges is presented and security assurance modelling is done through risk analysis using machine learning. In order to analyze the security risk in terms of threats and attacks for cloud computing environments, the most recent dataset (ISOT Cloud Intrusion Dataset) is used for intrusion detection under cloud computing environments. The methodology involves the implementation of multiple supervised machine learning algorithms like support vector machine (SVM), random forest (RF), logistic regression (LR), Naïve Bayes (NB), Artificial Neural Network (ANN), K-nearest Neighbor (kNN) to identify & classify intrusions for cloud environment. As a result, accuracy of the proposed SVM model is evaluated as 99.2%. The performance metrics of various machine learning implementation models are also compared & investigated using parameters like accuracy, AUC, F1, precision, and recall. The results are represented as confusion matrices. The outcome of this work will further help the network security administrator to mitigate the real time attacks under cloud computing environments.