Agu, Emmanuel O.
To make smartphone authentication more convenient and encourage usage of more secure methods, we designed a system, LOBS, that would authenticate users by recognizing their behavior patterns. LOBS constructed behavioral signatures by examining visible WiFi networks, GPS location, accelerometer data, battery usage, and when the screen was turned off and on. It used a neural network trained on the user’s historical data to analyze the latest data and determine a trust score, measuring how likely that data was to be from the same person, and authenticating the user if it was high enough. We evaluated LOBS with a study that used data gathered from six people over a week. The results we obtained were too low for LOBS to be commercially marketable, but much higher than random chance.
Worcester Polytechnic Institute
Major Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.