Cloud Computing Security Optimization via Algorithm Implementation

Abstract

There has been a growing need for significant improvements in cloud computing security ? to ensure that operations and data interactions in the cloud keep abreast with the dynamic nature of information technology. Motivated by the quest for cloud computing security, this paper has examined different approaches that most of the previous scholarly investigations (which focus on the adoption of machine learning in cloud computing security) have proposed ? towards better threat detection. The paper has begun with a general algorithm responsible for establishing the summation of risk levels before proceeding to more advanced algorithms through which threats to cloud data could be determined. Imperative to note is that the advanced approaches have been found to embrace anomaly detection and signature detection, translating into a proposed hybrid model for threat detection in the cloud. Whereas a major weakness is that the proposed model is not compared to another competitive model, its strength lies in the capacity to give an insight into ways in which certain time frames and profile categories could be specified, leading to a better classification of cloud user profiles and the eventual detection of anomalies.