Graduate Thesis Or Dissertation
 

Towards Deep Learning Model Portability for Domain-Agnostic Device Fingerprinting

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/x920g4884

Descriptions

Attribute NameValues
Creator
Abstract
  • In recent years, RF (Radio Frequency) device fingerprinting using deep learning has emerged as a method of identifying devices solely by their RF transmissions. Conventional approaches to this type of device fingerprinting are not portable to different domains. That is, if a model for this purpose is trained on data from one domain, the model will not perform well on data from a different but related domain. For RF fingerprinting, changing the receiver used, the day on which data was captured, or the configuration settings of transmitters all amount to changing the domain. This work proposes a technique that, using metric learning and a calibration process, enables a model trained with data from one domain to perform well on data from another domain. This is accomplished with only a small amount of training data from the target domain and without changing the weights of the model, which makes the technique computationally quick. This work evaluates the effectiveness of the proposed technique on RF data captured using a testbed of real devices in a variety of different scenarios. The results of this evaluation show that this technique is viable and especially useful for applications where computational resources are restricted.
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language
Embargo reason
  • Pending Publication
Embargo date range
  • 2022-06-17 to 2023-07-18

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details GaskinJaredC2022.pdf 2022-08-01 Public Download