Real time motion-based authentication for smartwatch

Smartwatches become increasingly powerful and popular. These personal devices carry multiple sensors that continuously measure, collect, and analyze various sensitive personal information. Therefore, a strong and user friendly authentication mechanism is much needed to prevent illegitimate accesses to those devices. However, traditional protection approaches are far from sufficient and desirable for smartwatches. In this work, we present our recent study on developing and testing a motion-based real time authentication system for smartwatch. Our system applies behavioral biometrics collected from a smartwatch to verify the person who wears the watch. We have developed a prototype application using Android Wear to authenticate users in real time. We tested our system against two types of attacks to evaluate its resilience to attacks. We recruited five volunteers in our preliminary evaluation, from which some interesting findings were discovered. Our preliminary experimental results indicate that real time motion-based authentication is viable and promising.