Real-time Device Fingerprinting and Re-identification in GNU Radio
Abstract
WiFi device fingerprinting and re-identification (RFFI) are critical functions for wireless security, mobility intelligence, and spectrum sharing applications. However, rapid prototyping and evaluation of fingerprint extraction and classification models remains a challenging task. Model performance evaluation requires exploring various environmental conditions, emitter types, and more. To streamline this process, we introduce gr-mobrffi — an out-of-tree GNU Radio project for real-time evaluation of device fingerprinting and re-identification models, available on GitHub. The gr-mobrffi GNU Radio blocks are designed to ingest WiFi frame preambles and produce vector embeddings to fingerprint and re-identify devices. We evaluate gr-mobrffi by performing real-time fingerprinting and re-identification on twelve WiFi emitters, while capturing WiFi probe requests with an AntSDR running OpenWiFi, and a custom Rust app. Indoor testing demonstrates the accuracy of our framework on fingerprint matching and re-identification by displaying WiFi device labels to a GUI.
Downloads
Published
Issue
Section
License
- I grant gnuradio.org a perpetual, non-exclusive license to distribute this article.
- I certify that I have the right to grant this license.
- I understand that submissions cannot be completely removed once accepted.
- I understand that gnuradio.org reserves the right to reclassify or reject any submission.