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.
[1]
Mengjun Xie,et al.
MotionAuth: Motion-based authentication for wrist worn smart devices
,
2015,
2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).
[2]
Alex X. Liu,et al.
Secure unlocking of mobile touch screen devices by simple gestures: you can see it but you can not do it
,
2013,
MobiCom.
[3]
Shridatt Sugrim,et al.
User-generated free-form gestures for authentication: security and memorability
,
2014,
MobiSys.
[4]
Hongyuan Zha,et al.
LatentGesture: active user authentication through background touch analysis
,
2014,
Chinese CHI '14.
[5]
Heinrich Hußmann,et al.
Touch me once and i know it's you!: implicit authentication based on touch screen patterns
,
2012,
CHI.
[6]
Parth H. Pathak,et al.
Finger-writing with Smartwatch: A Case for Finger and Hand Gesture Recognition using Smartwatch
,
2015,
HotMobile.