Publication:
Toward Generalizable Device Identification with Radio Frequency Fingerprint
| cris.virtual.department | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| cris.virtual.department | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| cris.virtual.department | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| cris.virtual.department | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| cris.virtual.orcid | 0009-0003-3299-453X | |
| cris.virtual.orcid | 0000-0003-1152-6617 | |
| cris.virtual.orcid | 0000-0003-0064-5020 | |
| cris.virtual.orcid | 0000-0002-1499-3782 | |
| cris.virtualsource.department | c5e628ef-e419-4d62-9ba9-bea5b592e744 | |
| cris.virtualsource.department | a2b34a52-0296-4181-842d-18e16639a1d7 | |
| cris.virtualsource.department | 0890472f-b07c-459b-b27e-54ab6db1557d | |
| cris.virtualsource.department | ff3b6b19-1b9b-4d92-89ba-4b833fe2bef7 | |
| cris.virtualsource.orcid | c5e628ef-e419-4d62-9ba9-bea5b592e744 | |
| cris.virtualsource.orcid | a2b34a52-0296-4181-842d-18e16639a1d7 | |
| cris.virtualsource.orcid | 0890472f-b07c-459b-b27e-54ab6db1557d | |
| cris.virtualsource.orcid | ff3b6b19-1b9b-4d92-89ba-4b833fe2bef7 | |
| dc.contributor.author | Nhem, Thayheng | |
| dc.contributor.author | Weyn, Maarten | |
| dc.contributor.author | Peeters, Michael | |
| dc.contributor.author | Berkvens, Rafael | |
| dc.date.accessioned | 2026-11-02T14:18:24Z | |
| dc.date.available | 2026-11-02T14:18:24Z | |
| dc.date.createdwos | 2026 | |
| dc.date.issued | 2026 | |
| dc.description.abstract | Radio Frequency Fingerprint (RFF) is a widely investigated methodology for identifying wireless devices. It refers to unique signal characteristics caused by hardware imperfections in a device's radio front-end. While deep learning models have shown strong performance in classifying known devices using RFF, they struggle to generalize to unseen devices. It often produces overlapping and cluttered feature representations. In this work, we propose using the FlexiPrint framework with a contrastive center loss to extract features from any new devices and cluster them. We conduct experiments on a dataset of 25 devices transmitting Wi-Fi signals. We train different supervised models using 20 devices for comparison. We then test those models on the remaining 5 devices and show that our proposed approach can extract features from the unknown devices beyond the training set with a Silhouette clustering score of 0.6209, which is significantly higher than the baseline model with a score of 0.0441. We also visualize the learned features using t-SNE, which further confirms the improved clustering of device features, demonstrating the potential generalizability to new devices. | |
| dc.description.wosFundingText | This research is partially funded by Research Foundation - Flanders (FWO) PESSO project under grant number: G018522N. | |
| dc.identifier.doi | 10.1109/wcnc65185.2026.11555343 | |
| dc.identifier.isbn | 979-8-3315-7730-8 | |
| dc.identifier.issn | 1525-3511 | |
| dc.identifier.uri | https://imec-publications.be/handle/20.500.12860/60680 | |
| dc.language.iso | eng | |
| dc.provenance.editstepuser | greet.vanhoof@imec.be | |
| dc.publisher | IEEE | |
| dc.relation.ispartofseries | IEEE Wireless Communications and Networking Conference | |
| dc.source.beginpage | 1 | |
| dc.source.conference | IEEE Wireless Communications and Networking Conference (WCNC) | |
| dc.source.conferencedate | 2026-04-13 | |
| dc.source.conferencelocation | Kuala Lumpur | |
| dc.source.endpage | 6 | |
| dc.source.journal | 2026 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC | |
| dc.source.numberofpages | 6 | |
| dc.subject.keywords | OPEN-SET | |
| dc.subject.keywords | TRANSMITTER | |
| dc.title | Toward Generalizable Device Identification with Radio Frequency Fingerprint | |
| dc.type | Proceedings paper | |
| dspace.entity.type | Publication | |
| imec.internal.crawledAt | 2026-06-17 | |
| imec.internal.source | crawler | |
| imec.internal.wosCreatedAt | 2026-11-02 | |
| Files | ||
| Publication available in collections: |