Benchmarking of Cancelable Biometrics for Deep Templates

TL;DR

This paper benchmarks various cancelable biometric schemes on deep learning-based templates across multiple biometric modalities, evaluating their security and recognition performance according to ISO standards, and provides open-source code for reproducibility.

Contribution

It introduces a comprehensive benchmarking framework for cancelable biometrics on deep templates, including new baseline schemes and extensive evaluation across biometric types.

Findings

BioHashing and IoM schemes show high recognition accuracy.

Some schemes exhibit strong unlinkability and irreversibility.

Open-source implementation facilitates reproducibility.

Abstract

In this paper, we benchmark several cancelable biometrics (CB) schemes on different biometric characteristics. We consider BioHashing, Multi-Layer Perceptron (MLP) Hashing, Bloom Filters, and two schemes based on Index-of-Maximum (IoM) Hashing (i.e., IoM-URP and IoM-GRP). In addition to the mentioned CB schemes, we introduce a CB scheme (as a baseline) based on user-specific random transformations followed by binarization. We evaluate the unlinkability, irreversibility, and recognition performance (which are the required criteria by the ISO/IEC 24745 standard) of these CB schemes on deep learning based templates extracted from different physiological and behavioral biometric characteristics including face, voice, finger vein, and iris. In addition, we provide an open-source implementation of all the experiments presented to facilitate the reproducibility of our results.