Secure data classification using superior naive classifier in agent based mobile cloud computing

Abstract

The explosive growth of cloud computing had resulted in the growth of fields such as ubiquitous computing, mobile cloud computing, Big Data Analytics and Cyber Physical Systems etc., Mobile Cloud Computing (MCC) is the integration of Mobile computing and Cloud computing and has gained tremendous popularity in recent years. In MCC, mobile users access the cloud services with the mobile device. Generally, the users of mobile cloud can select their services from the broker using an agent. There is an agreement between the users and service provider called SLA. Data are of varying types and they require different security levels based on their requirement. Classification of Mobile user's data is a time-consuming process. A superior naive classifier for secure data classification in agent based mobile cloud computing is proposed in this paper. The agent classifies the user's data into three different groups namely, low, medium, high. Then, the data are encrypted using Advanced Encryption Standards (AES). Encrypted data is transferred to the broker for selecting for suitable service agent.But the broker has many to one relationship with service agents. Then the data is sent to the cloud service provider for storage. The stored data is then homomorphically encrypted which enables the cloud provider and cloud user to process the data without the need for decryption. Performance analysis demonstrates that our proposed method reduces classification time and provides better security and integrity on mobile cloud data.