Skip to content

Design and Implementation of Hybrid CNN-Transformer Architecture for Face Anti-Spoofing

Sep 2026 · Natural Resources for Human Health · 0 citations · 29 references

TL;DR

This paper introduces HybridLivenessNet, a novel deep neural architecture that combines MobileNetV3-Small as a computationally efficient convolutional feature extractor with a multi-head Transformer encoder, thus capturing diverse and complementary representations at the local texture and global spatial levels.

Abstract

Biometric face recognition systems are progressively being used in security-sensitive areas and are vulnerable to presentation attacks (PAs) such as printed photograph recaptures, video replay attacks and 3D silicone mask attacks. Face Anti-Spoofing (FAS) also known as liveness detection is the first line of defence against such attacks. In this paper, we introduce HybridLivenessNet, a novel deep neural architecture that combines MobileNetV3-Small as a computationally efficient convolutional feature extractor with a multi-head Transformer encoder, thus capturing diverse and complementary representations at the local texture and global spatial levels. The proposed approach is trained and tested on the LCC FASD dataset with 11,247 annotated facial images in real and spoofed classes. During a 100-epoch training process with AdamW optimization, ReduceLROnPlateau adaptive scheduling strategy, strong dropout regularization and multi-pattern data augmentation, HybridLivenessNet attains its peak validation accuracy (98.47%) at epoch 9 and provides stable performance ranging from 98.03% to 98.27% from epoch 20 till 100, which suggests a stable convergence without over-fitting. The method offers a good balance of computational cost and detection performance, making it ideal for implementation in real-life systems with limited resources. In addition, we analyse and discuss training dynamics, learning rate decay, and epoch-wise accuracy curves.

View source

Similar papers

Open access Oct 2026

A Lightweight Face Anti-Spoofing Framework with Spoof Artifact Enhancement and Adaptive Feature Fusion

Face recognition is widely used for biometric authentication in applications such as mobile devices, financial services, intelligent surveillance, access control, and border security. However, face recognition systems remain vulnerable to presentation attacks, including printed photographs, replay attacks, and three-di...

Mudunuru Suneel, Banothu Yedukondala Venkata Naga Raja Swamy, Madhava Rao Maganti et al. · 0 citations
Conference Open access Sep 2026

Adaptive Face Region-based Vision Transformer for Video Deepfake Detection

Attention maps consistently identify eye region, nasolabial folds, and mouth region, areas typically involved in face-swap and reenactment manipulations, providing some evidence that the model's decisions are based on meaningful facial regions, in contrast to basing them on spurious clues.

I. V, Ravali Neela, Bhavishya Chowdary Borra et al. · 0 citations
Open access Sep 2026

COMPARATIVE EVALUATION OF DEEPFAKE DETECTION MODELS FOR SECURE REMOTE BIOMETRIC VERIFICATION

Results indicate that hybrid convolutional-transformer architectures generalize to boundary-free synthesis in a way that purely convolutional detectors do not, and that an open-source model can approach commercial detection quality without transmitting biometric data to a third party.

N. Dzhaliuk, V. Khoma, Y. Khoma · 0 citations
Conference Open access Sep 2026

HEL-CAW-Net: Face Liveness Detection Using Light Intensity-Aware Convolutional Attentional W-Net Model

Face liveness detection is a major component in securing biometric authentication systems from spoofing attacks with recorded video and printed photos. Therefore, numerous detection methods have been developed to detect face liveness, but they face notable disadvantages, including higher computational complexity, poor...

Sneha Sankhe, Megharani Patil · 0 citations
Review Open access Nov 2026

FACE SPOOFING DETECTION USING HYBRID BINARY STATISTICAL IMAGE FEATURES-GAUSSIAN FILTER

Face presentation attacks threaten the dependability of facial biometric authentication, particularly when conventional RGB cameras are exposed to print and replay artefacts. Existing texture descriptors are computationally attractive but remain sensitive to noise, illumination variation, and image degradation, whereas...

Taofik Abiodun Ahmed, Tosho Abdulrauf, M. Gbolagade · 0 citations
Open access Sep 2026

A HYBRID AI-DRIVEN FRAMEWORK FOR HIGH-PERFORMANCE FACIAL SKETCH RECOGNITION IN BIOMETRIC IDENTIFICATION SYSTEMS

Objective: Facial sketch recognition has been an issue of concern in biometrics in forensics as there is low accuracy of sketch-to-photo recognition of sketches in heterogeneous visual conditions. Method: In this paper, it is suggested that a hybrid AI-based framework can incorporate the use of a CNN backbone to extrac...

ALaa KHudhair Ali · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.