An Effective Approach to Continuous User Authentication for Touch Screen Smart Devices

Abstract

Due to the rapid increase in the use of personal smart devices, more sensitive data is stored and viewed on these smart devices. This trend makes it easier for attackers to access confidential data by physically compromising (including stealing) these smart devices. Currently, most personal smart devices employ one of the one-time user authentication schemes, such as four-to-six digits, fingerprint or pattern-based schemes. These authentication schemes are often not good enough for securing personal smart devices because the attackers can easily extract all the confidential data from the smart device by breaking such schemes, or by keeping the authenticated session open on a physically compromised smart device. In addition, existing re-authentication or continuous authentication techniques for protecting personal smart devices use centralized architecture and require servers at a centralized location to train and update the learning model used for continuous authentication, which impose additional communication overhead. In this paper, an approach is presented to generating and updating the authentication model on the user's smart device with user's gestures, instead of a centralized server. There are two major advantages in this approach. One is that this approach continuously learns and authenticates finger gestures of the user in the background without requiring the user to provide specific gesture inputs. The other major advantage is to have better authentication accuracy by treating uninterrupted user finger gestures over a short time interval as a single gesture for continuous user authentication.