An Authenticated Key Exchange Scheme for Efficient Security-Aware Scheduling of Scientific Applications in Cloud Computing

Instead of purchasing and maintaining their own computing infrastructure, scientists can now run data-intensive scientific applications in cloud computing environment by facilitating its vast storage and computation capabilities. During the scheduling of such scientific applications for execution, various computation data flows will happen between the controller and computing server instances. Amongst various quality-of-service (QoS) metrics, data security is one of the greatest concerns to scientists because their data may be intercepted or stolen by malicious parties during those data flows. An existing typical method for addressing this issue is to apply Internet Key Exchange (IKE) scheme to generate and exchange session keys, and then to apply these keys for performing symmetric-key encryption which will encrypt those data flows. However, the IKE scheme suffers from low efficiency due to its low performance of asymmetric-key crypto logical operations over a large amount of data and high-density operations which are exactly the characteristics of scientific applications. In this paper, we propose Cloud Computing Background Key Exchange (CCBKE), a novel authenticated key exchange scheme that aims at efficient security-aware scheduling of scientific applications. Our scheme is designed based on randomness-reuse strategy and Internet Key Exchange (IKE) scheme. Theoretical analyses and simulation results demonstrate that, compared with the IKE scheme, our CCBKE scheme can significantly improve the efficiency by dramatically reducing time consumption and computation load without sacrificing the level of security.