KinWrite: Handwriting-Based Authentication Using Kinect
Date: April 2013
Publication: Proceedings of the 20th Annual Network & Distributed System Security Symposium, NDSS 2013
Publisher: Internet Society
Source 1: http://www.internetsociety.org/sites/default/files/10_2_0.pdf
Source 2: http://www.cse.sc.edu/~tian9/papers/ndss13.pdf
Abstract or Summary:
Password-based authentication is easy to use but its security is bounded by how much a user can remember. Biometrics-based authentication requires no memorization but ‘resetting’ a biometric password may not always be possible. In this paper, we propose a user-friendly authentication system (KinWrite) that allows users to choose arbitrary, short and easy-to-memorize passwords while providing resilience to password cracking and password theft. KinWrite lets users write their passwords in 3D space and captures the handwriting motion using a low cost motion input sensing device—Kinect. The low resolution and noisy data captured by Kinect, combined with low consistency of in-space handwriting, have made it challenging to verify users. To overcome these challenges, we exploit the Dynamic Time Warping (DTW) algorithm to quantify similarities between handwritten passwords. Our experimental results involving 35 signatures from 18 subjects and a brute-force attacker have shown that KinWrite can achieve a 100% precision and a 70% recall (the worst case) for verifying honest users, encouraging us to carry out a much larger scale study towards designing a foolproof system.