Publication:
Identification of a smartphone user via keystroke analysis

Loading...
Thumbnail Image
Authors
Fleming, Samuel B.
Subjects
Android
behavioral biometrics
free-text
fixed-text
k-nearest neighbors
keystroke analysis
smartphone
touchscreen
Advisors
Martell, Craig
Gondree, Mark
Date of Issue
2014-03
Date
Mar-14
Publisher
Monterey, California: Naval Postgraduate School
Language
Abstract
Keystroke analysis has been an accepted method for user identification and authentication since the early 1980s. Most of the research in this field of biometrics has focused on traditional computer keyboards, with very few experiments performed on touchscreen keyboards found on modern smartphones. This study focused on identifying a smartphone user based on typing samples input by copying pre-written text, as well as spontaneously-authored free text. Features used for identification were duration of key press, as well as bigram and trigram transitions. User classification based on duration features proved to be successful in 70 percent of inputs to our k-nearest neighbors classifier.
Type
Thesis
Description
Series/Report No
Department
Computer Science
Other Units
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Collections