查看文章

Conventional computer systems or mobile devices authenticate users only at the initial login session, which can be a serious critical security flaw. To resolve the problem, the systems need continuous and transparent user authentication methods that continuously monitor and authenticate users based on some biometric traits. A new method for continuous user authentication is based on the way they interact with the touch screen of a smartphone. This method authenticates smartphone users by continuously monitoring their finger movements on the touch screen. Based on a set of 30 behavioral features, the authors built proof-of-concept classifiers that can pinpoint a target user among 41 users with very low equal error rate. Given the non-trivial error rates, this kind of touch-based analysis is qualified as a complementary authentication mechanism.