# Iris Liveness Detection using a Cascade of Dedicated Deep Learning Networks

arXiv: https://arxiv.org/abs/2105.14009 · HTML: https://mlsanity.com/paper/2105.14009/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 28 May 2021.

## Builds on (most cited first, 10 of 10)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation](https://mlsanity.com/paper/1901.01708/) (2019)
- [Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Edition](https://mlsanity.com/paper/2009.00749/) (2020)
- [Presentation Attack Detection for Iris Recognition: An Assessment of the State of the Art](https://mlsanity.com/paper/1804.00194/) (2018)
- [Deep Learning-Based Feature Extraction in Iris Recognition: Use Existing Models, Fine-tune or Train From Scratch?](https://mlsanity.com/paper/2002.08916/) (2020)
- [Style Your Face Morph and Improve Your Face Morphing Attack Detector](https://mlsanity.com/paper/2004.11435/) (2020)
- [Ensemble of Multi-View Learning Classifiers for Cross-Domain Iris Presentation Attack Detection](https://mlsanity.com/paper/1811.10068/) (2018)
- [CNN Hyperparameter tuning applied to Iris Liveness Detection](https://mlsanity.com/paper/2003.00833/) (2020)
- [Open Source Presentation Attack Detection Baseline for Iris Recognition](https://mlsanity.com/paper/1809.10172/) (2018)

## Built on by (most cited first, 9 of 9)

- [Deep Learning for Iris Recognition: A Survey](https://mlsanity.com/paper/2210.05866/) (2022)
- [Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Edition](https://mlsanity.com/paper/2310.04541/) (2023)
- [Towards Iris Presentation Attack Detection with Foundation Models](https://mlsanity.com/paper/2501.06312/) (2025)
- [A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detection](https://mlsanity.com/paper/2412.07199/) (2024)
- [Synthetic Periocular Iris PAI from a Small Set of Near-Infrared-Images](https://mlsanity.com/paper/2107.12014/) (2021)
- [Impact of Face Image Quality Estimation on Presentation Attack Detection](https://mlsanity.com/paper/2209.15489/) (2022)
- [An Incremental Gray-box Physical Adversarial Attack on Neural Network Training](https://mlsanity.com/paper/2303.01245/) (2023)
- [Internal Structure Attention Network for Fingerprint Presentation Attack Detection from Optical Coherence Tomography](https://mlsanity.com/paper/2303.11034/) (2023)
- [LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Security](https://mlsanity.com/paper/2506.06759/) (2025)

## Abstract (arXiv)

Iris pattern recognition has significantly improved the biometric authentication field due to its high stability and uniqueness. Such physical characteristics have played an essential role in security and other related areas. However, presentation attacks, also known as spoofing techniques, can bypass biometric authentication systems using artefacts such as printed images, artificial eyes, textured contact lenses, etc. Many liveness detection methods that improve the security of these systems have been proposed. The first International Iris Liveness Detection competition, where the effectiveness of liveness detection methods is evaluated, was first launched in 2013, and its latest iteration was held in 2020. This paper proposes a serial architecture based on a MobileNetV2 modification, trained from scratch to classify bona fide iris images versus presentation attack images. The bona fide class consists of live iris images, whereas the attack presentation instrument classes are comprised of cadaver, printed, and contact lenses images, for a total of four scenarios. All the images were pre-processed and weighted per class to present a fair evaluation. This proposal won the LivDet-Iris 2020 competition using two-class scenarios. Additionally, we present new three-class and four-class scenarios that further improve the competition results. This approach is primarily focused in detecting the bona fide class over improving the detection of presentation attack instruments. For the two, three, and four classes scenarios, an Equal Error Rate (EER) of 4.04%, 0.33%, and 4,53% was obtained respectively. Overall, the best serial model proposed, using three scenarios, reached an ERR of 0.33% with an Attack Presentation Classification Error Rate (APCER) of 0.0100 and a Bona Fide Classification Error Rate (BPCER) of 0.000. This work outperforms the LivDet-Iris 2020 competition results.