Introducing Nylon Face Mask Attacks: A Dataset for Evaluating Generalised Face Presentation Attack Detection

TL;DR

This paper introduces a new dataset featuring Nylon Face Masks as realistic presentation attack instruments to evaluate face recognition systems' robustness against advanced spoofing methods.

Contribution

It presents a novel dataset with diverse NFM attack samples and benchmarks existing PAD methods, highlighting the need for more generalisable detection techniques.

Findings

Significant variability in PAD performance against NFMs

NFMs closely mimic real facial geometry, challenging existing methods

The dataset enables evaluation of PAD robustness in real-world scenarios

Abstract

Face recognition systems are increasingly deployed across a wide range of applications, including smartphone authentication, access control, and border security. However, these systems remain vulnerable to presentation attacks (PAs), which can significantly compromise their reliability. In this work, we introduce a new dataset focused on a novel and realistic presentation attack instrument called Nylon Face Masks (NFMs), designed to simulate advanced 3D spoofing scenarios. NFMs are particularly concerning due to their elastic structure and photorealistic appearance, which enable them to closely mimic the victim's facial geometry when worn by an attacker. To reflect real-world smartphone-based usage conditions, we collected the dataset using an iPhone 11 Pro, capturing 3,760 bona fide samples from 100 subjects and 51,281 NFM attack samples across four distinct presentation scenarios involving both humans and mannequins. We benchmark the dataset using five state-of-the-art PAD methods to evaluate their robustness under unseen attack conditions. The results demonstrate significant performance variability across methods, highlighting the challenges posed by NFMs and underscoring the importance of developing PAD techniques that generalise effectively to emerging spoofing threats.