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.
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.· International Journal of Eng...· 0 citations
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.· 2026 10th International Conf...· 0 citations
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· Cybersecurity: Education, Sc...· 0 citations
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· 2026 7th International Confe...· 0 citations
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· International Journal of Nat...· 0 citations
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· Journal for Technology and S...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.