TY - GEN
T1 - Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift
AU - Chen, Jun
AU - Wong, Weng Keen
AU - Hamdaoui, Bechir
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Domain adaptation
KW - RF fingerprinting
KW - contrastive learning
KW - deep neural networks
KW - device classification
UR - http://www.scopus.com/inward/record.url?scp=85202886861&partnerID=8YFLogxK
U2 - 10.1109/ICC51166.2024.10622173
DO - 10.1109/ICC51166.2024.10622173
M3 - Conference contribution
AN - SCOPUS:85202886861
T3 - IEEE International Conference on Communications
SP - 3567
EP - 3572
BT - ICC 2024 - IEEE International Conference on Communications
A2 - Valenti, Matthew
A2 - Reed, David
A2 - Torres, Melissa
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 59th Annual IEEE International Conference on Communications, ICC 2024
Y2 - 9 June 2024 through 13 June 2024
ER -