A Multi-Attack Iris Spoof Detection Framework: An Enhanced CNN-Siamese Network

Author

Pooja Rai, Priyesh Kanungo

Abstract

 Iris spoof detection is essential for protecting biometric recognition systems against presentation attacks such as printed images, contact lenses, and digitally generated iris patterns. This work proposes a CNN-based Siamese network for detecting iris spoofing using genuine iris images and simulated attack variations. The model learns discriminative representations from pairs of iris images and determines whether they belong to the same or different classes using pairwise distance. Multiple spoofing scenarios, including print-like appearance, contact-lens effects, and frequency-spectrum manipulation, are incorporated to evaluate the robustness of the approach. The proposed framework reports strong and consistent performance of ≈97.9% on IIT Delhi iris dataset, across all accounted metrics; accuracy, precision, recall, and F1-score. Further, it reports an AUC of 1.00 supporting the strong discrimination capability between genuine and spoofed image specifically on simulation the frequency based synthetic iris-attack instruments. The proposed method is also compared with a few baseline existing methods for analyzing its performance and computational complexity under resource-limited enviornment.

Keywords

Appearance-based attack simulation, Biometric System and Security,Deep learning, Iris spoof detection,Siamese Network.

Full Text:

Download Paper PDF

References

[1] Jordan Nelson, Abraham Luck, Vannessa Candies, “Fingerprint Spoof Detection Using Machine Learning and Multimodal Biometrics”, Computer Security and Reliability, 2024

[2] Neenu Daniel, A. Anitha, “Texture and quality analysis for face spoofing detection”, Computers & Electrical Engineering, Volume 94, September 2021, 107293, Elsevier

[3] Safaa El‐Din, Yomna, Mohamed N. Moustafa, and Hani Mahdi. "Deep convolutional neural networks for face and iris presentation attack detection: Survey and case study." IET Biometrics 9, no. 5 (2020): 179-193.

[4] Sharma, Deepika, and Arvind Selwal. "Cascading adaptive binary image feature maps with vision transformer for iris spoof detection." Applied Soft Computing 170 (2025): 112713.

[5] Sheng-Hsun Hsieh, Yung-Hui Li, Wei Wang, Chung-Hao Tien, “A Novel Anti-Spoofing Solution for Iris Recognition Toward Cosmetic Contact Lens Attack Using Spectral ICA Analysis”, doi: 10.3390/s18030795,2018, National Library of Medicine.

[6] Chung Nguyen Tran et al. “A Fast Iris Liveness Detection for Embedded Systems using Textural Feature Level Fusion Algorithm , International Conference on Industry Sciences and Computer Science Innovation, Procedia Computer Science 237 (2024) 858–865,  Elsevier

[7] K. -C. Lin and Y. -M. Chen, "A High-Security-Level Iris Recognition System Based on Multi- Scale Dominating Feature Points," in IEEE Signal Processing Letters, vol. 31, pp. 1600-1604, 2024

[8] A. Agarwal, A. Noore, M. Vatsa and R. Singh, "Generalized Contact Lens Iris Presentation Attack Detection," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 4, no. 3, pp. 373-385, July 2022

[9] Juan E. Tapia ,Sebastian Gonzalez, Christoph Busch, “Iris Liveness Detection Using a Cascade of Dedicated Deep Learning Networks”, IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, VOL. 17, 2022

[10] Maciej Szymkowski, Piotr Jasiński,  Khalid Saeed, “Iris‑based human identity recognition with machine learning methods and discrete fast Fourier transform“, Innovations in Systems and Software Engineering (2021) 17:309–317, https://doi.org/10.1007/s11334-021-00392-9, Springer

[11] M. Choudhary, V. Tiwari and U. Venkanna, "Iris Liveness Detection Using Fusion of Domain-Specific Multiple BSIF and DenseNet Features," in IEEE Transactions on Cybernetics, vol. 52, no. 4, pp. 2370-2381, April 2022

[12] Gupta, Priyanshu, Shipra Behera, Mayank Vatsa, and Richa Singh. "On iris spoofing using print attack." In 2014 22nd international conference on pattern recognition, pp. 1681-1686. IEEE, 2014

[13] Sharma, Deepika, and Arvind Selwal. "IensNet: A novel and efficient approach for iris spoof detection via ensemble of deep models." Multimedia Tools and Applications (2025): 1-30

[14] Kumar, S. U. N. I. L., VIJAY KUMAR Lamba, and S. U. R. E. N. D. E. R. Jangra. "Anti-Spoofing for Iris Recognition With Contact Lens Detection." Adv Appl Math Sci 19, no. 5 (2020): 397-406

[15] Zhuo, Wenqi, Wei Wang, Hui Zhang, and Jing Dong. "Irisguard: image forgery detection for iris anti-spoofing." In Chinese Conference on Biometric Recognition, pp. 602-612. Cham: Springer Nature Switzerland, 2022.

[16] “Implementation of iris based monitoring system using KNN in comparison with SVM for better accuracy,T. Bhargav; Bhuvaneswari Balachander, INTERNATIONAL CONFERENCE ON ADVANCEMENT IN DESIGN, DEVELOPMENT, ENGINEERING, PROCESSING, AND CHARACTERIZATION: ADDEPC 2021, https://doi.org/10.1063/5.0197601

[17] Fuzzy-CNN: Improving personal human identification based on IRIS recognition using LBP features, Mashael M. Khayyat, Nuha Zamzami , Li Zhang , Michele Nappi, Muhammad Umer, Volume 83, June 2024, 103761,Journal of Information Security and Applications.https://doi.org/10.1016/j.jisa.2024.103761.

[18] Synthesizing Iris Images using Generative Adversarial Networks, ,Shivangi Yadav, Arun Ross, arXiv:2404.17105v2, May 2024

[19] Ramachandra, Raghavendra & Venkatesh, Sushma. (2025). SpectraIrisPAD: Leveraging Vision Foundation Models for Spectrally Conditioned Multispectral Iris Presentation Attack Detection. 10.48550/arXiv.2512.06103.

[20] Tapia Farias, Juan & González Soler, Lázaro & Busch, Christoph. (2025). Towards Iris Presentation Attack Detection with Foundation Models. 10.48550/arXiv.2501.06312.

[21] Fang, Meiling & Damer, Naser & Boutros, Fadi & Kirchbuchner, Florian & Kuijper, Arjan. (2020). Deep Learning Multi-layer Fusion for an Accurate Iris Presentation Attack Detection. 10.23919/FUSION45008.2020.9190424.

[22] Sharma, Renu & Ross, Arun. (2020). D-NetPAD: An Explainable and Interpretable Iris Presentation Attack Detector. 10.48550/arXiv.2007.01381.

 

 

 

 

 

 

Share your valuable work from Social Media Buttons