Entropy aided RF-DNA fingerprint learning from Gabor-based images

Author

Mohamed Alfatih Taha, University of Tennessee at ChattanoogaFollow

Committee Chair

Reising, Donald R.

Committee Member

Loveless, Thomas Daniel; Fadul, Mohamed M. K.

Department

Dept. of Electrical Engineering

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

The number of devices connected to the internet have been increasing and shape Internet of Things (IoT). The security of IoT is an issue due to the use of weak or no encryption. Specific Emitter Identification (SEI) was introduced to overcome this issue by introduce RF-DNA fingerprinting exploring the PHY layer features. Recently, The SEI performance improved by the usage of the signal’s Time Frequency (TF) representation and accelerated using the Deep learning (DL) Convolutional Neural Network (CNN). While the classification accuracy has been improved from using raw signals learning the amount of data generated is large and computationally expensive. This work investigate the usage of statistical thresholds like entropy applied to ”tiles” selected from the signals’ TF representation to reduce the amount of data generated. The results show that the entropy based data reduction decrease the average classification accuracy by 0.86% compared to the usage of the full gray-scale image at 30dB. The usage of enhanced tiles selection algorithms shows an improvement in the average classification accuracy by 25% from the original tile selection procedure at 9dB.

Acknowledgments

I dedicate this thesis to my parents, friends, and family, who have been my rock and my motivation throughout this academic journey. Your unwavering support and encouragement have been the driving force behind my success. To my parents, I owe you everything. You have always believed in me, even when I didn’t believe in myself. Your constant love and support have given me the strength to pursue my dreams and overcome any obstacle. To my friends and family, thank you for your constant encouragement and for believing in me when I needed it the most. Your unwavering support has given me the courage to pursue my passion. To my thesis supervisor, Dr. Reising, I am grateful for your guidance and expertise. Your mentorship has been instrumental in shaping my academic growth. To my colleagues, Dr. Fadul and Joshua Tyler, thank you for your unwavering support and for contributing your expertise to this project. This thesis is dedicated to all of you, for your unyielding love, support, and encouragement. I am grateful for the sacrifices you have made on my behalf, and I hope that this work makes you proud. Thank you for being my source of strength and motivation, and for making this journey worthwhile.

Degree

M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.

Date

5-2023

Subject

Internet of things; Deep learning (Machine learning); Computer security

Keyword

Deep Learning, Time-Frequency Representation, Specific Emitter Identification, Entropy, Feature Extraction

Discipline

Electrical and Computer Engineering

Document Type

Masters theses

DCMI Type

Text

Extent

x, 50 leaves

Language

English

Rights

http://rightsstatements.org/vocab/InC/1.0/

License

http://creativecommons.org/licenses/by-nc-nd/3.0/

Date Available

5-31-2024

Recommended Citation

Taha, Mohamed Alfatih, "Entropy aided RF-DNA fingerprint learning from Gabor-based images" (2023). Masters Theses and Doctoral Dissertations.
https://scholar.utc.edu/theses/795