Modeling Home IoT Traffic using Users’ in-Home Activities for Detection of Anomalous Operations

In this paper, we modeled home IoT traffic based on users’ in-home activities by the sensors and operations of home IoT devices. Then, we applied the model to the detection of anomalous operations. We evaluated our model by using a dataset obtained in an actual home environment. The results demonstrated that the detection using our method achieved 72.3% detections with less than 20.1% misdetections.