Introducing Nylon Face Mask Attacks: A Dataset for Evaluating Generalised Face Presentation Attack Detection
This addresses security risks in applications like smartphone authentication and border security by providing a dataset for evaluating detection methods against emerging spoofing threats, though it is incremental as it focuses on a specific new attack type.
The authors tackled the vulnerability of face recognition systems to presentation attacks by introducing a dataset of Nylon Face Masks, a novel and realistic 3D spoofing instrument, and found significant performance variability across five state-of-the-art detection methods, with the dataset containing 3,760 bona fide and 51,281 attack samples.
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.