Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

3-2012

Abstract

In this paper, we present a new way of generating behavioral (not biometric) fingerprints from the cellphone usage data. In particular, we explore if the generated behavioral fingerprints are memorable enough to be remembered by end users. We built a system, called HuMan, that generates fingerprints from cellphone data. To test HuMan, we conducted an extensive user study that involved collecting about one month of continuous usage data (including calls, SMSes, application usage patterns etc.) from 44 Symbian and Android smartphone users. We evaluated the memorable fingerprints generated from this rich multi-context data by asking each user to answer various authentication questions generated from the fingerprints. Results show that the fingerprints generated by HuMan are remembered by the user to some extent and were moderately secure against attacks even by family members and close friends.

Keywords

Cell phone, End users, Mobile users, Symbian, Usage data, Usage patterns, User study

Discipline

Computer Sciences | Information Security | Software Engineering

Research Areas

Cybersecurity; Software and Cyber-Physical Systems

Publication

2012 IEEE International Conference on Pervasive Computing and Communications Workshops, Lugano, Switzerland, 19-23 March 2012: Proceedings

First Page

479

Last Page

482

ISBN

9781467309059

Identifier

10.1109/PerComW.2012.6197540

Publisher

IEEE

City or Country

Piscataway, NJ

Copyright Owner and License

Authors/LARC

Additional URL

https://doi.org/10.1109/PerComW.2012.6197540

Download

Share

COinS