FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection

TL;DR

FoundPAD leverages foundation models with LoRA adaptation for face presentation attack detection, achieving high generalization to unseen scenarios with limited or synthetic training data.

Contribution

This work introduces FoundPAD, the first adaptation of foundation models for PAD, demonstrating improved generalization and efficiency in face attack detection tasks.

Findings

High generalization to unseen domains

Effective with limited and synthetic training data

Competitive results across various scenarios

Abstract

Although face recognition systems have seen a massive performance enhancement in recent years, they are still targeted by threats such as presentation attacks, leading to the need for generalizable presentation attack detection (PAD) algorithms. Current PAD solutions suffer from two main problems: low generalization to unknown cenarios and large training data requirements. Foundation models (FM) are pre-trained on extensive datasets, achieving remarkable results when generalizing to unseen domains and allowing for efficient task-specific adaption even when little training data are available. In this work, we recognize the potential of FMs to address common PAD problems and tackle the PAD task with an adapted FM for the first time. The FM under consideration is adapted with LoRA weights while simultaneously training a classification header. The resultant architecture, FoundPAD, is highly generalizable to unseen domains, achieving competitive results in several settings under different data availability scenarios and even when using synthetic training data. To encourage reproducibility and facilitate further research in PAD, we publicly release the implementation of FoundPAD at https://github.com/gurayozgur/FoundPAD .