Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategies

TL;DR

This paper reviews iris image synthesis techniques, discusses the risks of biometric data leakage, and explores mitigation strategies to ensure privacy when using generated iris datasets for biometric research.

Contribution

It provides a comprehensive overview of iris synthesis methods and analyzes privacy risks and mitigation strategies for biometric data leakage.

Findings

GAN-based and diffusion models can generate high-fidelity iris images

Biometric feature leakage from synthetic datasets poses privacy risks

Mitigation strategies are essential for privacy preservation

Abstract

This paper presents a comprehensive overview of iris image synthesis methods, which can alleviate the issues associated with gathering large, diverse datasets of biometric data from living individuals, which are considered pivotal for biometric methods development. These methods for synthesizing iris data range from traditional, hand crafted image processing-based techniques, through various iterations of GAN-based image generators, variational autoencoders (VAEs), as well as diffusion models. The potential and fidelity in iris image generation of each method is discussed and examples of inferred predictions are provided. Furthermore, the risks of individual biometric features leakage from the training sets are considered, together with possible strategies for preventing them, which have to be implemented should these generative methods be considered a valid replacement of real-world biometric datasets.