IoTPerimeter: A Passive Fingerprinting of Smart Environment using Graph-based Features

Integration of orthogonal services in a single IoT device makes it difficult to apply traditional mechanism of device identification vis-a-vis reconnaissance of a smart home environment. Rule based white listing of IoT devices becomes difficult when IP camera is integrated with a smart bulb for example. In this paper, we aim to build a graph of (private or public) IP addresses used by IoT devices within a specific time window and check if the graph is consistent across other time windows. We plan to design and implement a system, IoTPerimeter, that can construct such graphs and extracts features in order to finger a smart environment. We evaluate the system performance using publicly available three datasets. Our system extracts 121 features and utilize six supervised machine learning algorithms. Our preliminary analysis shows that a same environment can have up to 20-30% of outliers. Only about four features have more than 10% of importance score and others have a low score.