Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift

Jun Chen, Weng Keen Wong, Bechir Hamdaoui

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise from variations in the channel conditions and environmental settings, potentially degrading the accuracy of RF-based device classification when testing and training data is collected in different domains. This paper introduces a novel solution that leverages contrastive learning to mitigate this domain shift problem. Contrastive learning, a state-of-the-art self-supervised learning approach from deep learning, learns a distance metric such that positive pairs are closer (i.e. more similar) in the learned metric space than negative pairs. When applied to RF fingerprinting, our model treats RF signals from the same transmission as positive pairs and those from different transmissions as negative pairs. Through experiments on wireless and wired RF datasets collected over several days, we demonstrate that our contrastive learning approach captures domain-invariant features, diminishing the effects of domain-specific variations. Our results show large and consistent improvements in accuracy (10.8% to 27.8%) over baseline models, thus underscoring the effectiveness of contrastive learning in improving device classification under domain shift.

Original languageEnglish
Title of host publicationICC 2024 - IEEE International Conference on Communications
EditorsMatthew Valenti, David Reed, Melissa Torres
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3567-3572
Number of pages6
ISBN (Electronic)9781728190549
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event59th Annual IEEE International Conference on Communications, ICC 2024 - Denver, United States
Duration: 9 Jun 202413 Jun 2024

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Conference

Conference59th Annual IEEE International Conference on Communications, ICC 2024
Country/TerritoryUnited States
CityDenver
Period9/06/2413/06/24

Keywords

  • Domain adaptation
  • RF fingerprinting
  • contrastive learning
  • deep neural networks
  • device classification

Fingerprint

Dive into the research topics of 'Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift'. Together they form a unique fingerprint.

Cite this