Synthetic Iris Presentation Attack using iDCGAN

TL;DR

This paper introduces iDCGAN, a deep learning framework for generating realistic synthetic iris images to evaluate and challenge iris recognition systems, highlighting the need for improved attack detection methods.

Contribution

The paper presents a novel deep learning-based method, iDCGAN, for creating highly realistic synthetic iris images to test and improve presentation attack detection.

Findings

Synthetic iris images can successfully deceive iris recognition systems.

Current detection methods like DESIST struggle to distinguish synthetic from real iris images.

Mitigating synthetic presentation attacks is crucial for iris biometric security.

Abstract

Reliability and accuracy of iris biometric modality has prompted its large-scale deployment for critical applications such as border control and national ID projects. The extensive growth of iris recognition systems has raised apprehensions about susceptibility of these systems to various attacks. In the past, researchers have examined the impact of various iris presentation attacks such as textured contact lenses and print attacks. In this research, we present a novel presentation attack using deep learning based synthetic iris generation. Utilizing the generative capability of deep convolutional generative adversarial networks and iris quality metrics, we propose a new framework, named as iDCGAN (iris deep convolutional generative adversarial network) for generating realistic appearing synthetic iris images. We demonstrate the effect of these synthetically generated iris images as presentation attack on iris recognition by using a commercial system. The state-of-the-art presentation attack detection framework, DESIST is utilized to analyze if it can discriminate these synthetically generated iris images from real images. The experimental results illustrate that mitigating the proposed synthetic presentation attack is of paramount importance.