VibAuth: Enabling Accurate, Usable, and Deployable User Authentication by Leveraging Vibration

Abstract

User authentication is essential to prevent the leakage of a user's sensitive information in mobile and IoT devices. Several attempts have been made for supporting accurate user authentication, but compromising usability and deployability. In this work, we propose a novel user authentication method, called VibAuth, that is accurate, usable, and deployable, especially by leveraging vibration. It simply generates vibrations by using wrist-wearable devices (e.g., smartwatches). The vibrations are transmitted through a user's hand and eventually captured by motion sensors (e.g., accelerometers). VibAuth then extracts user-specific features and authenticates users. Our experiments with a prototype of VibAuth demonstrate that we can support a reasonable accuracy in user authentication, by using only commodity and easily-accessible devices.