Open Set RF Fingerprinting using Generative Outlier Augmentation

TL;DR

This paper introduces generative deep learning methods to augment training data for open set RF fingerprinting, enabling better recognition of authorized devices and rejection of unauthorized ones, especially with limited known unauthorized samples.

Contribution

It proposes novel data augmentation techniques using generative models to improve open set RF fingerprinting without needing extensive unauthorized transmitter data.

Findings

Data augmentation significantly improves open set classification accuracy.

Methods perform well even with limited unauthorized transmitter samples.

Enhanced detection of unauthorized transmitters in WiFi RF fingerprinting.

Abstract

RF devices can be identified by unique imperfections embedded in the signals they transmit called RF fingerprints. The closed set classification of such devices, where the identification must be made among an authorized set of transmitters, has been well explored. However, the much more difficult problem of open set classification, where the classifier needs to reject unauthorized transmitters while recognizing authorized transmitters, has only been recently visited. So far, efforts at open set classification have largely relied on the utilization of signal samples captured from a known set of unauthorized transmitters to aid the classifier learn unauthorized transmitter fingerprints. Since acquiring new transmitters to use as known transmitters is highly expensive, we propose to use generative deep learning methods to emulate unauthorized signal samples for the augmentation of training datasets. We develop two different data augmentation techniques, one that exploits a limited number of known unauthorized transmitters and the other that does not require any unauthorized transmitters. Experiments conducted on a dataset captured from a WiFi testbed indicate that data augmentation allows for significant increases in open set classification accuracy, especially when the authorized set is small.