arXiv releases BLE device fingerprinting dataset and testbed
Original title: Dataset and Experimental Testbed for Deep Learning-Based Bluetooth Device Fingerprinting
Large-scale raw IQ dataset from 31 Bluetooth Low Energy devices across varied environments plus evaluation of domain-robust radio-frequency fingerprinting models.
The paper introduces a comprehensive BLE dataset of raw IQ transmissions captured from 31 commercial devices over multiple days, locations, temperatures and receiver hardware. It also presents a case study evaluating state-of-the-art domain-robust deep learning techniques for radio frequency fingerprinting to improve generalization in unseen environments such as different rooms or carrier frequencies.
- Dataset includes raw IQ transmissions from 31 distinct BLE devices
- Captured across diverse days, locations, environments, temperatures and frequencies
- Evaluates domain-robust RFFP techniques for real-world AI reliability
- Addresses failure of DL models in unseen configurations
- First comparative evaluation on common full-system hardware platform
From the original article
1 min read at arxiv.orgAI-enabled wireless networks have emerged as vital components of future-generation wireless communication systems. Among various wireless architectures, Bluetooth Low Energy (BLE) networks have attracted significant research interest due to their widespread adoption and low cost.
By Haytham Albousayri · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.