Haven't I Seen You Before? Assessing Identity Leakage in Synthetic Irises

TL;DR

This paper investigates how GAN-generated iris images can unintentionally reveal training data identities, analyzing the leakage risk over training time and across different iris matchers.

Contribution

It provides a detailed analysis of identity leakage in synthetic iris images generated by StyleGAN3, highlighting when and how personal biometric data may leak during training.

Findings

Most synthetic iris samples do not leak identities

Some generated samples nearly perfectly match training data

Leakage risk varies with GAN training progress

Abstract

Generative Adversarial Networks (GANs) have proven to be a preferred method of synthesizing fake images of objects, such as faces, animals, and automobiles. It is not surprising these models can also generate ISO-compliant, yet synthetic iris images, which can be used to augment training data for iris matchers and liveness detectors. In this work, we trained one of the most recent GAN models (StyleGAN3) to generate fake iris images with two primary goals: (i) to understand the GAN's ability to produce "never-before-seen" irises, and (ii) to investigate the phenomenon of identity leakage as a function of the GAN's training time. Previous work has shown that personal biometric data can inadvertently flow from training data into synthetic samples, raising a privacy concern for subjects who accidentally appear in the training dataset. This paper presents analysis for three different iris matchers at varying points in the GAN training process to diagnose where and when authentic training samples are in jeopardy of leaking through the generative process. Our results show that while most synthetic samples do not show signs of identity leakage, a handful of generated samples match authentic (training) samples nearly perfectly, with consensus across all matchers. In order to prioritize privacy, security, and trust in the machine learning model development process, the research community must strike a delicate balance between the benefits of using synthetic data and the corresponding threats against privacy from potential identity leakage.