MobRFFI: Non-cooperative Device Re-identification for Mobility Intelligence

2025-03-04

AI Summary

In WiFi-based mobile sensing, MAC address randomization impedes device re-identification, hindering trajectory tracking and congestion analysis. To address this, we propose a non-cooperative, MAC-agnostic device re-identification method. Our approach introduces three key innovations: (1) the first cross-day robust multi-receiver radio-frequency (RF) fingerprint fusion mechanism, eliminating reliance on specific frame types; (2) a deep encoder-based hardware impairment feature extraction module; and (3) a fingerprint cascaded fusion strategy integrated with an unsupervised device representation learning framework to achieve persistent device identification. Evaluated on the WiSig dataset, our method achieves 100% accuracy for single-day and 94% for multi-day re-identification. On our newly collected MobRFFI dataset—captured in real urban environments—multi-receiver fusion boosts multi-day accuracy from 41% to 100%, demonstrating strong efficacy and robustness under practical deployment conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Motion & Tracking

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

WiFi-based mobility monitoring in urban environments can provide valuable insights into pedestrian and vehicle movements. However, MAC address randomization introduces a significant obstacle in accurately estimating congestion levels and path trajectories. To this end, we consider radio frequency fingerprinting and re-identification for attributing WiFi traffic to emitting devices without the use of MAC addresses. We present MobRFFI, an AI-based device fingerprinting and re-identification framework for WiFi networks that leverages an encoder deep learning model to extract unique features based on WiFi chipset hardware impairments. It is entirely independent of frame type. When evaluated on the WiFi fingerprinting dataset WiSig, our approach achieves 94% and 100% device accuracy in multi-day and single-day re-identification scenarios, respectively. We also collect a novel dataset, MobRFFI, for granular multi-receiver WiFi device fingerprinting evaluation. Using the dataset, we demonstrate that the combination of fingerprints from multiple receivers boosts re-identification performance from 81% to 100% on a single-day scenario and from 41% to 100% on a multi-day scenario.

Problem

• Overcome MAC address randomization in WiFi mobility monitoring.
• Develop AI-based device fingerprinting for accurate re-identification.
• Enhance re-identification accuracy using multi-receiver WiFi fingerprints.

Innovation

• AI-based device fingerprinting using deep learning
• Radio frequency fingerprinting without MAC addresses
• Multi-receiver WiFi fingerprinting boosts re-identification accuracy