Continuous User Verification via Mouse Activities
Author(s): Khandaker Abir Rahman, Ryan Moormann, Danielle Dierich, Md. Shafaeat Hossain

Date: December 2015
Publication: Communications in Computer and Information Science, Volume 566
Page(s): 170 - 181
Publisher: Springer
Source 1: http://dx.doi.org/10.1007/978-3-319-26404-2_14 - Subscription or payment required

Abstract or Summary:
Behavioral biometrics such as mouse dynamics are gaining attention these days to address the limitations of conventional verification systems. In this paper we present a novel method to continuously verify a user via their mouse activities. Our method, based on comparing mouse activities against a simple statistical profile, was tested over 76,500 mouse activities collected from 45 users. A total of 354,375 genuine and impostor verification attempts have been performed by deploying 175 different verifier setups. In our experiments, we achieved an impressive low Equal Error Rate (EER) of 6.70 %. On average the EER was 13.42 %. We opine that, our method can complement regular verification systems and can better serve for continuous verification purpose because of its simplicity.



Do you have additional information to contribute regarding this research paper? If so, please email siteupdates@passwordresearch.com with the details.

<-- Back to Authentication Research Paper Index





[Home] [About Us] [News] [Research]

Copyright © 2016 PasswordResearch.com