# Deep convolutional neural networks for face and iris presentation attack detection: Survey and case study

arXiv: https://arxiv.org/abs/2004.12040 · HTML: https://mlsanity.com/paper/2004.12040/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [Digital and Physical Face Attacks: Reviewing and One Step Further](https://mlsanity.com/paper/2209.14692/) (2022)
- [A Compact Deep Learning Model for Face Spoofing Detection](https://mlsanity.com/paper/2101.04756/) (2021)
- [Introduction to Presentation Attack Detection in Iris Biometrics and Recent Advances](https://mlsanity.com/paper/2111.12465/) (2021)
- [Adversarial Unsupervised Domain Adaptation Guided with Deep Clustering for Face Presentation Attack Detection](https://mlsanity.com/paper/2102.06864/) (2021)
- [A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method](https://mlsanity.com/paper/2408.09752/) (2024)

## Abstract (arXiv)

Biometric presentation attack detection is gaining increasing attention. Users of mobile devices find it more convenient to unlock their smart applications with finger, face or iris recognition instead of passwords. In this paper, we survey the approaches presented in the recent literature to detect face and iris presentation attacks. Specifically, we investigate the effectiveness of fine tuning very deep convolutional neural networks to the task of face and iris antispoofing. We compare two different fine tuning approaches on six publicly available benchmark datasets. Results show the effectiveness of these deep models in learning discriminative features that can tell apart real from fake biometric images with very low error rate. Cross-dataset evaluation on face PAD showed better generalization than state of the art. We also performed cross-dataset testing on iris PAD datasets in terms of equal error rate which was not reported in literature before. Additionally, we propose the use of a single deep network trained to detect both face and iris attacks. We have not noticed accuracy degradation compared to networks trained for only one biometric separately. Finally, we analyzed the learned features by the network, in correlation with the image frequency components, to justify its prediction decision.