Identification of Wearable Devices with Bluetooth

2018-02-21

IEEE Transactions on Sustainable Computing

AI Summary

Current wearable device security mechanisms solely authenticate user identity while neglecting device-level trustworthiness, exposing systems to unauthorized access, passive eavesdropping, and data leakage. To address this gap, we propose the first non-intrusive wearable device fingerprinting framework tailored for Bluetooth Classic. Our approach extracts protocol-layer features via passive over-the-air sniffing—without requiring device modification or active interaction—and enables fine-grained, device-level identification. We innovatively integrate 20 machine learning algorithms—including SVM, Random Forest, and XGBoost—to automatically select the optimal classifier. Evaluated on commercial smartwatches across multiple brands, our framework achieves an average accuracy of 98.5%, with both precision and recall at 98.3%. This significantly enhances device identity assurance and provides robust, real-time threat intelligence for wearable cybersecurity.

Abstract

With wearable devices such as smartwatches on the rise in the consumer electronics market, securing these wearables is vital. However, the current security mechanisms only focus on validating the user not the device itself. Indeed, wearables can be (1) unauthorized wearable devices with correct credentials accessing valuable systems and networks, (2) passive insiders or outsider wearable devices, or (3) information-leaking wearables devices. Fingerprinting via machine learning can provide necessary cyber threat intelligence to address all these cyber attacks. In this work, we introduce a wearable fingerprinting technique focusing on Bluetooth classic protocol, which is a common protocol used by the wearables and other IoT devices. Specifically, we propose a non-intrusive wearable device identification framework which utilizes 20 different Machine Learning (ML) algorithms in the training phase of the classification process and selects the best performing algorithm for the testing phase. Furthermore, we evaluate the performance of proposed wearable fingerprinting technique on real wearable devices, including various off-the-shelf smartwatches. Our evaluation demonstrates the feasibility of the proposed technique to provide reliable cyber threat intelligence. Specifically, our detailed accuracy results show on average 98.5 percent, 98.3 percent precision and recall for identifying wearables using the Bluetooth classic protocol.

Problem

• Identifying unauthorized wearable devices via Bluetooth
• Detecting passive insider or outsider wearable threats
• Preventing information leakage from wearable devices

Innovation

• Machine learning for wearable device fingerprinting
• Bluetooth classic protocol analysis
• Non-intrusive ML framework with 20 algorithms