Electronic Thesis/Dissertation
 

Utilizing Deep Learning Models to Detect Jamming and Spoofing Attacks on Unmanned Aerial Vehicles

Open Access Deposited

This area of study aims to enhance detection of malicious attacks on Unmanned Aerial Vehicle (UAV) sensors. As the use of UAVs—aerial devices that operate without a human pilot onboard—expands in various fields, the threats posed by jamming and spoofing attacks have become increasingly significant. This research explores the application of Deep Learning (DL) techniques, specifically Multilayer Perceptron (MLP) and Radial Basis Function Network (RBFN) models, to enhance the detection of these malicious activities targeting UAVs. By leveraging a comprehensive dataset simulating different jamming and spoofing scenarios, the researcher developed and trained these models to effectively identify and classify attacks with high accuracy, precision, recall and F-measure scores. The results highlight the potential of DL algorithms as key tools in proactively detecting malicious UAV operational activities, in turn ensuring precise and timely mitigation of these threats, including placing proactive measures in place to limit attacks.

Author Language Date created Type of Work License
  • All rights reserved
Rights statement GW Unit Degree Advisor Committee Member(s) Persistent URL

Notice to Authors

If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.

Thumbnail Title Date Uploaded Visibility Actions
Preview of NWEZE_gwu_0075A_17140.pdf NWEZE_gwu_0075A_17140.pdf 2025-04-09 Open Access