Effectively Identifying Wi-Fi Devices through State Transitions

2025-07-03

AI Summary

To address the insufficient robustness of Wi-Fi device identification under MAC address randomization, this paper proposes a device fingerprinting method based on dynamic modeling of management-frame state transitions. Unlike prior approaches relying solely on probe requests, we are the first to model the complete sequence of management-frame state transitions—including authentication, association, and disassociation—as a finite-state machine, and construct matrix-form features integrating structural and temporal dimensions: namely, a state-transition frequency matrix and normalized inter-arrival time encoding. Leveraging feature embedding and similarity matching—without requiring data frames—we achieve >86% identification accuracy across diverse real-world scenarios using management frames only. Further incorporating temporal burst aggregation yields significant performance gains, substantially outperforming state-of-the-art methods. Our core contribution lies in revealing and quantifying device-specific behavioral signatures inherent in management-frame protocol interactions, establishing a novel paradigm for privacy-preserving wireless device identification.

Technology Category

• Intelligent Robots: State Estimation
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Machine Learning: Privacy

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Wi-Fi management frames reveal structured communication patterns that persist even under randomization of MAC addresses. Prior approaches to associating randomized MAC addresses with devices primarily focus on probe requests, overlooking the broader set of management frames and their transition dynamics. This narrow focus limits their robustness in dense, real-world environments with high device mobility, where probe activity alone fails to yield stable and distinctive signatures. In this paper, we present a novel framework for fingerprinting Wi-Fi devices based on behavioral dynamics extracted from passively observed management frames. We model each device's behavior as a finite state machine and introduce matrix-based representations that encode both structural (state transition frequencies) and temporal (inter-state delays) characteristics. These matrices are embedded into compact feature vectors, enabling efficient similarity comparison. Through extensive evaluation in diverse real-world settings, our method achieves over 86% identification accuracy for non-randomized devices using only Wi-Fi management frames, with further improvements observed through temporal burst aggregation. Our findings are sufficient to uniquely and consistently characterize devices at scale, outperforming the state-of-the-art.

Problem

• Identifying Wi-Fi devices using state transition patterns
• Overcoming MAC randomization limitations in device tracking
• Improving accuracy in dense, mobile environments via management frames

Innovation

• Fingerprinting Wi-Fi devices via behavioral dynamics
• Matrix-based state transition and delay encoding
• High accuracy using passive management frame analysis