A swipe-based unlocking mechanism with supervised learning on smartphones: Design and evaluation

With the rapid development of mobile devices, smartphones have become common in people's daily lives, i.e., retrieving community happenings and connecting with peers. Due to the convenience, users often store a large amount of private information on their phones (e.g., photos) and use the phone to process sensitive operations (e.g., financial transactions). Thus, there is a great need to protect the devices from unauthorized access in order to avoid privacy leakage and financial loss. Passwords are the most widely used authentication method, but attackers can take over the phone after it is unlocked. Instead, behavioral authentication can verify current users in a continuous way, which can complement the existing authentication mechanisms like passwords. With the increasing capability of smartphone sensors, users can perform various touch actions to interact with their devices. Motivated by this, in this work, we focus on swipe behavior and develop SwipeVlock, a supervised unlocking mechanism on smartphones, which can authenticate users based on their way of swiping the phone screen with a background image. In the evaluation, we measure several typical supervised learning algorithms and conduct two user studies with over 150 participants. As compared with similar schemes, it is found that participants could perform well with SwipeVLock, i.e., with a success rate of 98% during login and retention.