Network flow analysis for detection and mitigation of Fraudulent Resource Consumption (FRC) attacks in multimedia cloud computing

Multimedia computing has evolved as a remarkable technology which provides services to view, create, edit, process, and search multimedia contents. All these multimedia services have high computational, bandwidth, and storage requirements. Therefore, multimedia cloud computing has gained appreciable popularity and acceptance in the past one decade. The convenience of cloud computing comes with financial burden. One of the fundamental features of cloud computing, which helps in reducing the financial worries of the multimedia service providers is the cloud's pay-as-you-go pricing model. However, the cloud's pricing model has also attracted adversaries that have hindered the migration of services and/or data by various organisations to the cloud. Through the cloud's pay-as-you-go pricing model, attackers usually target the financial viability of the cloud customers. Therefore, such attacks are capable to affect the long term availability of multimedia-services hosted on the public cloud. These attacks are known as Fraudulent Resource Consumption (FRC) attack. Therefore, research in the area of FRC attack detection and mitigation is important in motivating the organisations to adopt the public cloud platform. In this paper, we propose a novel approach based on network flow analysis at the victim side to detect and mitigate the FRC attacks against cloud-based services. Experiments were conducted using real world benchmark datasets to evaluate the performance of the proposed approach. Experimental outcomes suggest that our proposed approach is able to detect and mitigate the FRC attacks with satisfactory accuracy and low overhead.