Mobile Cloud Offloading for Malware Detections with Learning

Accurate malware detections on mobile devices such as smartphones require fast processing of a large number of data and thus cloud offloading can be used to improve the security performance of mobile devices with limited resources. The performance of malware detection with cloud offloading depends on the computation speed of the cloud, the population sharing the cloud resources and the bandwidth of the radio access. In the paper, we investigate the offloading rates of smartphones connecting to the same security server in a cloud under dynamic network bandwidths and formulate their interactions as a non-cooperative mobile cloud offloading game. The Nash equilibrium of the mobile cloud offloading game and the existence condition are presented. An offloading algorithm based on Q-learning is proposed for smartphones to determine their offloading rates for malware detection with unknown parameters such as transmission costs. Simulation results show that the proposed offloading strategy can achieve the optimal rate and improve the user's utility under dynamic network bandwidths.