Automated IoT device fingerprinting through encrypted stream classification

Abstract

The explosive growth of the Internet of Things (IoT) has enabled a wide range of new applications and services. Meanwhile, the massive scale and enormous heterogeneity (e.g., in device vendors and types) of IoT raise challenges in efficient network/device management, application QoS-aware provisioning, and security and privacy. Automated and accurate IoT device fingerprinting is a prerequisite step for realizing secure, reliable, and high-quality IoT applications. In this paper, we propose a novel data-driven approach for passive fingerprinting of IoT device types through automatic classification of encrypted IoT network flows. Based on an in-depth empirical study on the traffic of real-world IoT devices, we identify a variety of valuable data features for accurately characterizing IoT device communications. By leveraging these features, we develop a deep learning based classification model for IoT device fingerprinting. Experimental results using a real-world IoT dataset demonstrate that our method can achieve 99% accuracy in IoT device-type identification.