DMorphNet: Face Morphing Detection Using Generative Adversarial Networks and EfficientNet-B6

DOI

10.2991/978-94-6239-713-2_20How to use a DOI?

Keywords

Face Morphing Attack Detection; GAN-based Morphing; EfficientNet-B6; Support Vector Machine; Deep Feature Extraction; Biometric Security; Deep Learning

Abstract

In today's world, face recognition is widely used in biometric security systems like border control, passports, identity verification, and so on. These systems are vulnerable to face-morphing attacks, where two or more face images are blended together to make a real image that can fool a whole verification system. So considering this situation, our model will help to prevent such types of attacks. Existing methods fail to effectively detect such morphs’ images, especially under real-world conditions like compression, noise, or ageing effects. Therefore, there is a need for an efficient and accurate model to detect morphed faces using deep learning techniques and adversarial features. Python is used as the programming language, along with frameworks such as TensorFlow, Keras, and scikit-learn. The model we use is EfficientNet-B6. It is a deep convolutional neural network, which is designed for high accuracy and computational efficiency. It also balances the network depth, width & image resolution; it also provides strong representation of features for complex image patterns. For this network, the main tasks are face analysis or image classification. And the classifier we use, which is SVM, means “support vector machine. “ It is a supervised machine learning classifier that can separate the data into different classes. It focuses on improving generalization and reduces overfitting. SVM is more robust, stable, and effective for high-dimensional features. It enhances the classification accuracy and consistency.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sayali Subhash Gawade
AU  - Anushka Vijay Gujar
AU  - Akshata Ramesh Harekar
AU  - Anushka Sanjay Jadhav
AU  - Swapnali Ravindra Teli
PY  - 2026
DA  - 2026/06/25
TI  - DMorphNet: Face Morphing Detection Using Generative Adversarial Networks and EfficientNet-B6
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 277
EP  - 291
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_20
DO  - 10.2991/978-94-6239-713-2_20
ID  - Gawade2026
ER  -