Insider Threats, who are cloud internal users, cause very serious problems, which in terns, leads to devastating attacks for both individuals and organizations. Although, most of the attentions, in the real world, is for the outsider attacks, however, the most damaging attacks come from the Insiders. In cloud computing, the problem becomes worst in which the number of insiders are maximized and hence, the amount of data that can be breached and disclosed is also maximized. Consequently, insiders' threats in the cloud ought to be one of the top most issues that should be handled and settled. Classical solutions to defend against insiders’ threats might fail short as it is not easy to track both activities of the insiders as well as the amount of knowledge an insider can accumulate through his/her privileged accesses. Such accumulated knowledge can be used to disclose critical information –which the insider is not privileged to- through expected dependencies that exist among different data items that reside in one or more nodes of the cloud. This paper provides a solution that suits well the specialized nature of the above mentioned problem. This solution takes advantage of knowledge bases by tracking accumulated knowledge of insiders through building Knowledge Graphs (KGs) for each insider. It also takes advantage of Mobile Edge Computing (MEC) by building a fog layer where a mitigation unit -resides on the edge- takes care of the insiders threats in a place that is as close as possible to the place where insiders reside. As a consequence, this gives continuous reactions to the insiders’ threats in real-time, and at the same time, lessens the overhead in the cloud. The MEC model to be presented in this paper utilizes a knowledgebase approach where insiders’ knowledge is tracked and modeled. In case an insider knowledge accumulates to a level that is expected to cause some potential disclosure of private data, an alarm will be raised so that expected actions should be taken to mitigate this risk. The knowledgebase approach involves generating Knowledge Graphs (KGs), Dependency Graphs (DGs) where a Threat Prediction Value (TPV) is evaluated to estimate the risk upon which alarms for potential disclosure are raised. Experimental analysis has been conducted using CloudExp simulator where the results have shown the ability of the proposed model to raise alarms for potential risks from insiders in a real time fashion with accurate precision
Querying and Searching Heterogeneous Knowledge Graphs in Real-time Linked Dataspaces