Honors Theses
Advisor
Chris Yakopcic
Department
Electrical and Computer Engineering
Publication Date
4-26-2020
Document Type
Honors Thesis
Abstract
Machine learning has become rapidly utilized in cybersecurity, rising from almost non-existent to currently over half of cybersecurity techniques utilized commercially. Machine learning is advancing at a rapid rate, and the application of new learning techniques to cybersecurity have not been investigate yet. Current technology trends have led to an abundance of household items containing microprocessors all connected within a private network. Thus, network intrusion detection is essential for keeping these networks secure. However, network intrusion detection can be extremely taxing on battery operated devices. The presented work presents a cyberattack detection system based on a multilayer perceptron neural network algorithm. To show that this system can operate at low power, the algorithm was executed on two commercially available minicomputer systems including the Raspberry PI 3 and the Asus Tinkerboard. An analysis of accuracy, power, energy, and timing was performed to study the tradeoffs necessary when executing these algorithms at low power. Our results show that these low power implementations are feasible, and a scan rate of more than 226,000 packets per second can be achieved from a system that requires approximately 5W to operate with greater than 99% accuracy.
Permission Statement
This item is protected by copyright law (Title 17, U.S. Code) and may only be used for noncommercial, educational, and scholarly purposes.
Keywords
Undergraduate research
eCommons Citation
Chisholm, Kayla, "Machine Learning for Cyberattack Detection" (2020). Honors Theses. 251.
https://ecommons.udayton.edu/uhp_theses/251
COinS
