HMM Based Cache Pollution Attack Detection for Edge Computing Enabled Mobile Social Networks

With the rapid advances of wireless technologies and popularization of mobile devices, edge computing boosts mobile social networks (MSNs) to allow mobile users to deliver, share, and exchange contents with each other. In particular, with edge caching, various content services can be provided to mobile users with improved Quality-of-Experience (QoE). However, edge caching is vulnerable to cache pollution attack (CPAttack), degrading content delivery. To tackle these problems, in this paper, we propose a hidden Markov model (HMM) based detection scheme against CPAttack in edge computing enabled MSNs. Specifically, we first present the CPAttack model with the observations of malicious behaviors. According to the CPAttack model, the caching state of each edge device is characterized in terms of request rate and cache hit rate. The HMM is exploited to detect the CPAttack with observation sequence of caching states. The simulation results demonstrate that the proposed scheme can efficiently improve edge devices' capability to detect CPAttack.