Accession Number:

AD1082655

Title:

Authenticating a Known User Through Behavioral Biometrics Using a Smartphone Accelerometer

Descriptive Note:

Technical Report

Corporate Author:

Naval Postgraduate School Monterey United States

Personal Author(s):

Report Date:

2017-12-01

Pagination or Media Count:

51.0

Abstract:

This thesis investigates the feasibility of authenticating a user through a behavioral biometric signature from smartphone accelerometer data. Using a Samsung Galaxy S7, acceleration in relation to the necessary equilibrium, postural state for a subject to orient a smartphone in order to read a headline article was measured and recorded by the MATLAB Mobile application. Twenty subjects1 known and 19 unknownwere used in the creation of a MATLAB machine-learning classifier. The classifier accurately distinguished an unknown subject from the known subject. Recommendations for future work include repeating the experiment with the latest smartphone devices as available, incorporating different sensors available to the MATLAB Mobile App, and introducing noise to spoof the known user.

Subject Categories:

  • Computer Programming and Software
  • Radio Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE