"Machine Learning-Based Classification of Wi-Fi Standards Using RF Sign" by Jeffrey A. Knight

Date of Award

3-2024

Document Type

Thesis

Degree Name

Master of Science in Cyber Operations

Department

Department of Electrical and Computer Engineering

First Advisor

Barry Mullins, PhD

Abstract

This research explores the application of AI methodologies in classifying RF signals within the IEEE 802.11 spectrum, focusing on differentiating Wi-Fi standards and router signatures. Utilizing a HackRF One Software Defined Radio (SDR) tuned to 2.4 GHz Channel 6, the research involved collecting raw samples from five different 802.11 routers, which are then transformed into constellation plots using a Python script. These plots served as the input for training a Convolutional Neural Network (CNN) model, aimed at classifying both Wi-Fi standards and router manufacturers. The model highlighted its ability to generalize to unfamiliar hardware. The methodologies and findings of this research, along with an analysis of the results, are presented.

AFIT Designator

AFIT-ENG-MS-24-M-017

Comments

A 12-month embargo was observed for posting this work on AFIT Scholar.

Distribution Statement A, Approved for Public Release. PA case number on file.

Share

COinS