Edge Intelligence Based Identification and Classification of Encrypted Traffic of Internet of Things

A detection model of Internet Things encrypted traffic based on edge intelligence is proposed in the paper, which can reduce communication times distributed gateways process as well establishment time, order to solve problems that it difficult carry out efficient classification and accurate identification Things. In this four new methods for are put forward, namely time-sequence behavior analysis, dynamic key analysis two-round filtering analysis. The experimental results show when sample size 1600, time less than 100 seconds, accuracy all more 92% recall rates them 83%.