A privacy-based SLA violation detection model for the security of cloud computing

Abstract

A Service Level Agreement (SLA) is a legal contract between any two parties to ensure an adequate Quality of Service (QoS). Most research on SLAs has concentrated on protecting the user data through encryption. However, these methods can not supervise a cloud service provider (CSP) directly. In order to address this problem, we propose a privacy-based SLA violation detection model for cloud computing based on Markov decision process theory. This model can recognize and regulate CSP's actions based on specific requirements of various users. Additionally, the model could make effective evaluation to the credibility of CSP, and can monitor events that user privacy is violated. Experiments and analysis indicate that the violation detection model can achieve good results in both the algorithm's convergence and prediction effect.