Electronic Thesis/Dissertation
 

Machine Learning Model to Detect Internet of Things Application Layer Attacks Using Constrained Application Protocol

Open Access Deposited

This research focuses on enhancing the constrained application protocol (CoAP) security by deploying machine learning techniques. As cyber-attacks targeting the internet of things (IoT) devices using the CoAP increase, the need for network defenses becomes more critical. Twelve CoAP features were evaluated to find out the most important features in determining cyber-attacks targeting CoAP communications. Among various models tested—Decision Tree, Gaussian Naïve Bayes, Convolutional Neural Network-Long Short-Term Memory, Extreme Gradient Boosting, and Random Forest—the Random Forest model emerged as the most effective in identifying cyber-attacks on CoAP communications. This study identifies the critical security features of CoAP and advances the application of machine learning in detecting CoAP cyber-attacks by evaluating various machine learning models and adding a generated dataset that captures CoAP attacks.

Author Language Keyword Date created Type of Work License
  • All rights reserved
Rights statement GW Unit Degree Advisor 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 Austin_gwu_0075A_16957.pdf Austin_gwu_0075A_16957.pdf 2025-04-11 Open Access