ESR 5: Countermeasure algorithms against subterfuge in mobile biometric systems

What has been achieved and the impact

Liveness detection for ear recognition:

Ear recognition technique has been widely applied to personal identification and verification systems due to its satisfying performance. However, its security may be an issue, since it was shown in our previous study that ear recognition systems may be vulnerable in an adversarial environment in which an adversary can camouflage as a legitimate user in order to mislead the system. This research proposes an ear liveness detection method with flash against 2D-spoofing attack along with ear print.

Pupil Dynamics for Iris Liveness Detection using Visible Light Spectrum on mobile device:

The primary objective of this research is to propose a complete methodology for face and iris liveness detection based on gaze tracking and pupil dynamics on visible spectrum in mobile devices. This method may serve as a composition of presentation attack detection in iris and face recognition systems, making them more secure. Due to a lack of public databases, that would support this paper, we will build our own iris capture device to register pupil size changes under the visible light stimuli, we will capture iris from users. 


I believe that if we continue this project, we might make a real-world application for liveness detection and it can save us against subterfuge not only in mobile biometric systems but also in all biometric systems.