A Machine Learning-Based Framework for Enhancing Data Security in Cloud of Things

Abstract

Cloud computing has arisen as a progressive model in the field of IoT. It runs on the bases of on-demand services which can be taken in a way that the users of the services can avail them based on their demand, not only this, the user can balance the resources on per demand. Cloud computing comes up with never-ending benefits, but being cost-effective is it’s the main merit. Security of cloud is the focused thing in this work. the data generated by IoT is huge in amount that low-power constrained find it difficult to handle, so this is what the clouding computing is here for. The combination of Cloud Computing and IOT is known as Cloud of Things (CoT). This fusion is solving the issues of storage but it also comes up with the challenges of security. To identify the issues of security, many researches has been done. These include the integrity and the confidentiality of data but it also identifies different kinds of CoT attacks, i.e. eavesdropping, forgery, flooding attacks, DOS, insider attacks etc. some researchers have also suggested some solutions, but there is still a need of finding the solutions that are comprehensive, intelligent and detailed. This research work will propose the theoretical framework of data security in CoT based on Machine Learning Techniques. This work will present some solutions that how can the machine learning techniques can be used to cope up with the threats against CoT.