Online Adaptive Personalization for Face Anti-spoofing

TL;DR

This paper introduces OAP, an online adaptive personalization method that enhances face anti-spoofing systems by adapting models in real-time using unlabeled data, improving robustness against spoofing attacks.

Contribution

The paper presents a lightweight online adaptation approach that can be integrated with existing anti-spoofing methods without storing original images, addressing distribution shifts in real scenarios.

Findings

OAP improves anti-spoofing accuracy on the SiW dataset.

OAP enhances performance in both single video and continual attack settings.

Ablation studies validate the effectiveness of design choices.

Abstract

Face authentication systems require a robust anti-spoofing module as they can be deceived by fabricating spoof images of authorized users. Most recent face anti-spoofing methods rely on optimized architectures and training objectives to alleviate the distribution shift between train and test users. However, in real online scenarios, past data from a user contains valuable information that could be used to alleviate the distribution shift. We thus introduce OAP (Online Adaptive Personalization): a lightweight solution which can adapt the model online using unlabeled data. OAP can be applied on top of most anti-spoofing methods without the need to store original biometric images. Through experimental evaluation on the SiW dataset, we show that OAP improves recognition performance of existing methods on both single video setting and continual setting, where spoof videos are interleaved with live ones to simulate spoofing attacks. We also conduct ablation studies to confirm the design choices for our solution.