Publication:
PLIO: Physical Layer Identification using One-shot Learning

Loading...
Thumbnail Image
Identifiers
Publication date
2021-10-04
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
The Internet of Things (IoT) is connecting a massive scale of everyday objects to the internet. We need to ensure the secure connectivity and authentication of these devices. Physical (PHY)-layer identification methods can distinguish between different devices by leveraging their unique hardware imperfections. But these methods typically require large quantities of training data which makes them impractical for large deployment scenarios. Also, these methods do not address the PHY-layer identification of new devices joining an IoT network. In this paper, we propose a PHY-layer identification method using one-shot learning that can identify new devices using the network solicitation packet of the devices as reference packets. We show that our method can accurately identify new devices without training, achieving a precision and recall over 80% even in the presence of 10 dBm noise. Furthermore, we show that with minimal retraining using only three packets from each device, we can accurately identify all devices in the IoT network with a precision and recall of 93%.
Description
Proceedings: 2021 IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems MASS 2021, 4-7 October 2021, Denver, CO, USA.
Keywords
RF fingerprinting, Security, Deep-learning
Bibliographic citation
Hazra, S., Voigt, T. & Yan, W. (4-7 October, 2021). PLIO: Physical Layer Identification using One-shot Learning [Proceedings]. 2021 IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems (MASS), Denver, CO, USA.