Deep Residual Learning for Face Anti-Spoofing: A Mathematical Framework for Optimized Skip Connections

Nurpeisova A. Shaushenova A. Kuznetsov O. Ispussinov A. Mutalova Z. Kassymova A.
September 2025 Multidisciplinary Digital Publishing Institute (MDPI)

Technologies
2025 #13 Issue 9

Face anti-spoofing is crucial for protecting biometric authentication systems. Presentation attacks using 3D masks and high-resolution printed images present detection challenges for existing methods. In this paper, we introduce a family of specialized CNN architectures, AttackNet, designed for robust face anti-spoofing with optimized residual connections and activation functions. The study includes the development of four architectures: baseline LivenessNet, AttackNetV1 with concatenation-based skip connections, AttackNetV2.1 with optimized activation functions, and AttackNetV2.2 with efficient addition-based residual learning. Our analysis demonstrates that element-wise addition in skip connections reduces parameters from 8.4 M to 4.2 M while maintaining performance. A comprehensive evaluation was conducted on four benchmark datasets: MSSpoof, 3DMAD, CSMAD, and Replay-Attack. Results show high accuracy (approaching 100%) on the 3DMAD, CSMAD, and Replay-Attack datasets. On the more challenging MSSpoof dataset, AttackNetV1 achieved 99.6% accuracy with an HTER of 0.004, outperforming the baseline LivenessNet (94.35% accuracy, 0.056 HTER). Comparative analysis with state-of-the-art methods confirms the superiority of the proposed approach. AttackNetV2.2 demonstrates an optimal balance between accuracy and computational efficiency, requiring 16.1 MB of memory compared to 32.1 MB for other AttackNet variants. Training time analysis shows twice the speed for AttackNetV2.2 compared to AttackNetV1. Architectural ablation studies highlight the crucial role of residual connections, batch normalization, and suitable dropout rates. Statistical significance testing verifies the reliability of the results (p-value < 0.001). The proposed architectures show excellent generalization ability and practical usefulness for real-world deployment in mobile and embedded systems.

biometric security , computer vision , convolutional neural networks , deep learning , face anti-spoofing , face recognition , liveness detection , machine learning , neural network architectures , presentation attack detection , residual and skip connections , spoofing attacks

Text of the article Перейти на текст статьи

Department of Information Systems, Faculty of Computer Systems and Professional Education, S. Seifullin Kazakh Agro Technical Research University, Astana, 010000, Kazakhstan
Department of Theoretical and Applied Sciences, eCampus University, Via Isimbardi 10, CO, Novedrate, 22060, Italy
Department of Intelligent Software Systems and Technologies, School of Computer Science and Artificial Intelligence, Karazin Kharkiv National University, 4 Svobody Sq., V.N, Kharkiv, 61022, Ukraine
Administration, Astana IT University, Mangilik El Avenue, 55/11, Astana, 010001, Kazakhstan
Economics, Information Technology and Vocational Education, Higher School of Information Technologies, Zhangir Khan University, Zhangir Khan 51, Uralsk, 090009, Kazakhstan

Department of Information Systems
Department of Theoretical and Applied Sciences
Department of Intelligent Software Systems and Technologies
Administration
Economics

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026