Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts

TL;DR

This paper introduces a novel device identification method using device latency and an accumulation score to account for wireless channel dynamics, achieving over 97% accuracy in real-world IoT scenarios.

Contribution

The work presents a new approach that leverages device latency and accumulation score to improve IoT device identification accuracy under wireless channel variability.

Findings

Achieves over 97% F1 score in real-world tests.

Demonstrates the impact of channel dynamics on device latency accuracy.

Outperforms previous methods with 75% F1 score when ignoring channel effects.

Abstract

Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. More importantly, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as "device latency," as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency. Specifically, this work introduces "accumulation score" as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency.