ANTISPOOFAI: A Deep Learning Framework for Face Spoof Detection

A Jyothi; G Amulya; T Nehareddy; G Amulya; G Meghana; G Rushika

doi:10.5281/zenodo.20003167

Authors

A Jyothi Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090
G Amulya Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090
T Nehareddy Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090
G Amulya Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090
G Meghana Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090
G Rushika Department of Computer Science and Engineering, G. Narayanamma Institute of Technology and Science, Hyderabad, India – 500090

DOI:

https://doi.org/10.5281/zenodo.20003167

Keywords:

Facial Recognition, Anti-Spoofing, Convolutional Neural Network (CNN), Siamese Network, Liveness Detection

Abstract

Facial recognition technology has been applied to smartphones, mobile payment systems, intelligent access systems, and surveillance systems. But with its wide application comes the susceptibility to spoofing attacks based on printed pictures, replayed videos, or face masks. The common anti-spoofing measures based on previous studies rely on the addition of more hardware components such as infrared cameras and depth cameras. This makes the systems more expensive to implement.To overcome these issues, the proposed work introduces a software-oriented facial anti-spoofing technique using the Streamlit platform that can function properly usingnormal cameras. The proposed approach utilizes Convolutional Neural Networks to extract facial characteristics and a Siamese Network to discriminate between actual and spoofed facial images. The proposed technique is efficient, hardware agnostic, scalable, and can be used successfully as a real-time or uploaded video analysis tool.

References

Shinde, S. R., et al. (2025). Enhancing face liveness detection: Novel deep CNN architectures for anti-spoofing. Engineering, Technology & Applied Science Research, 15(5), 27206–27212.

Huang, P.-K., et al. (2024). A survey on deep learning-based face anti-spoofing. APSIPA Transactions on Signal and Information Processing, 13(1).

Huang, Y., Zhang, W., & Wang, J. (2020). Deep frequent spatial temporal learning for face anti-spoofing. arXiv. https://arxiv.org/abs/2002.03723

Rahman, M. M., et al. (2026). ROS2-based real-time autonomous mapping and navigation: Integrating visual SLAM and sensor fusion with performance analysis under varying light. Measurement, 120695.

Gedam, P. W., Tiwari, A., & Dhabu, M. (2026). A flexible squeeze excited multi-modal feature fusion based vision transformer for face anti-spoofing in authentication system. Optics & Laser Technology, 199, 115045.

Long, X., Zhang, J., & Shan, S. (2025). Confidence aware learning for reliable face anti-spoofing. IEEE Transactions on Information Forensics and Security.

Adedapo, I. A., Odejobi, O., & Taiwo, T. (2025). Countermeasures against bias and spoofing in modern facial recognition systems.

Wang, Z., et al. (2020). Deep spatial gradient and temporal depth learning for face anti-spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Wu, H., et al. (2021). Dual spoof disentanglement generation for face anti-spoofing with depth uncertainty learning. IEEE Transactions on Circuits and Systems for Video Technology, 32(7), 4626–4638.

Xing, H., et al. (2025). Face anti-spoofing based on deep learning: A comprehensive survey. Applied Sciences, 15(12), 6891.