Faculty Advisor

Agu, Emmanuel O.

Abstract

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.

Publisher

Worcester Polytechnic Institute

Date Accepted

March 2018

Major

Computer Science

Project Type

Major Qualifying Project

Accessibility

Unrestricted

Advisor Department

Computer Science

Share

COinS