Dynamic Feature Extraction and User Classification using TouchAnalytics™

McLeod, Clay (2014) Dynamic Feature Extraction and User Classification using TouchAnalytics™. Undergraduate thesis, under the direction of Dr. Dawn Wilkins from Computer Science, University of Mississippi.

[img] Text
ElectronicThesis-ClayMcLeod.pdf - Accepted Version
Restricted to Repository staff only until 11 April 2015.

Download (1MB) | Request a copy


Security systems for modern computing devices suffer from a multitude of weaknesses that can render users helpless against an attack on their system. Various attempts at incorporating human characteristics into security systems have achieved varying levels of success in improving security. In this paper, we study the usefulness of TouchAnalytics™ - a second-level security system that attempts to authenticate a user based on touch-data gathered from an interaction with the device. Through the use of machine learning algorithms, we developed a system that is successful at au- thenticating users, achieving under 0.05% False Authentication Rate (FAR). We conclude that the removal of strictly defined training activities yields more characteristic data for each user, and thus, a more accurate system.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Machine Learning, Biometric Authentication, Mobile Security, TouchAnalytics, Artificial Intelligence
Creators: McLeod, Clay
Student's Degree Program(s): B.S. in Electrical Engineering
Thesis Advisor: Dr. Dawn Wilkins
Thesis Advisor's Department: Computer Science
Institution: University of Mississippi
Subjects: T Technology > T Technology (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Depositing User: Mr. Clay McLeod
Date Deposited: 29 Apr 2014 14:17
Last Modified: 29 Apr 2014 14:24
URI: http://thesis.honors.olemiss.edu/id/eprint/30

Actions (login required)

View Item View Item