Cloud-based user authentication with geo-temporal queries on smartphones

Smartphones are becoming more and more important in our daily life and carrying massive private data. Without a user authentication mechanism, an adversary may easily access all the sensitive information, such as contacts, messages, photos, credit card information and passwords. Therefore, a number of authentication techniques have been proposed and developed for mobile devices. Some of the most commonly used techniques include conventional password based scheme, pattern-based scheme, physiological biometric based techniques, etc. In this paper we focus on designing and developing an authentication scheme utilizing a series of geo-temporal queries for user authentication on smart phones. The basic idea is to use past knowledge on geographic and temporal (or geo-temporal) contextual perspectives to authenticate the user who wants to unlock the smart phone. On Android 4.3, we build a prototype App, which provides user authentication to unlock a Samsung Galaxy S4 smartphone with low power consumption.