Secure Lightweight Face Authentication with MTCNN and LightCNN for Digital Financial Services
DOI:
https://doi.org/10.62411/jcta.16276Keywords:
Biometric authentication, Biometric template protection, Blockchain, Digital financial services, Distance-based encryption, Face recognition, LightCNN, Mobile authenticationAbstract
Mobile face authentication for digital financial services must simultaneously satisfy recognition accuracy, computational efficiency, and biometric security under resource-constrained deployment conditions. This study proposes and evaluates a lightweight face-authentication framework that integrates detector–recognition pipeline optimization, protected biometric-template transformation, and blockchain-backed integrity support. Five face detection–recognition pipelines were systematically evaluated using a shared LightCNN-29v2 backbone fine-tuned on the Indonesian Muslim Student Face Dataset (IMSFD), with Mahalanobis-based Distance-Based Encryption (DBE) providing protected template matching and blockchain hash anchoring serving as an architectural integrity layer. Experiments on 3,660 images from 68 identities demonstrate that the MTCNN + LightCNN pipeline achieves the most favorable in-domain performance, reaching 94.95% accuracy, a ROC-AUC of 0.9970, an F1-score of 0.95, and successful processing of 3,546 out of 3,660 test images with an overall model size of approximately 5 MB. Applying Mahalanobis-based DBE further improves verification performance on IMSFD, increasing accuracy to 96.88% while reducing the False Acceptance Rate (FAR) from 0.83% to 0.18% and the False Rejection Rate (FRR) from 16.44% to 10.12%. Cross-dataset evaluation on LFW, CFP-FF, CFP-FP, AgeDB-30, CALFW, and CPLFW indicates that the proposed framework generalizes well to frontal-domain benchmarks but exhibits expected performance degradation under cross-pose and cross-age conditions due to distribution shift. Overall, the results demonstrate that detector selection is the dominant factor influencing end-to-end verification performance, while domain-specific fine-tuning and protected template matching are essential for secure and practical deployment in mobile financial authentication systems.References
M. R. Prasad and N. Thillaiarasu, “A Framework for Integrated Bank ATM Transactions Security Based on Multi‐Modal Biometric Authentication Using Adaptive and Attentive Assisted Mobilenet‐V3,” Comput. Intell., vol. 41, no. 4, Aug. 2025, doi: 10.1111/coin.70083.
J. Chi, C. Kim On, H. Zhang, and S. S. Chai, “A Review of Deep Convolutional Neural Networks in Mobile Face Recognition,” Int. J. Interact. Mob. Technol., vol. 17, no. 23, pp. 4–19, Dec. 2023, doi: 10.3991/ijim.v17i23.40867.
A. Baran and E. Bartuzi-Trokielewicz, “Face the Challenge—Generalization of Presentation Attack Detection,” Sensors, vol. 25, no. 18, p. 5792, Sep. 2025, doi: 10.3390/s25185792.
A. Hassani, J. Diedrich, and H. Malik, “Improving Monocular Facial Presentation–Attack–Detection Robustness with Synthetic Noise Augmentations,” Sensors, vol. 23, no. 21, p. 8914, Nov. 2023, doi: 10.3390/s23218914.
L. R. Zuama, D. R. I. M. Setiadi, A. Susanto, S. Santosa, H.-S. Gan, and A. A. Ojugo, “High-Performance Face Spoofing Detection using Feature Fusion of FaceNet and Tuned DenseNet201,” J. Futur. Artif. Intell. Technol., vol. 1, no. 4, pp. 385–400, Feb. 2025, doi: 10.62411/faith.3048-3719-62.
A. Howard et al., “Searching for MobileNetV3,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2019, pp. 1314–1324. doi: 10.1109/ICCV.2019.00140.
X. Wu, R. He, Z. Sun, and T. Tan, “A Light CNN for Deep Face Representation With Noisy Labels,” IEEE Trans. Inf. Forensics Secur., vol. 13, no. 11, pp. 2884–2896, Nov. 2018, doi: 10.1109/TIFS.2018.2833032.
M. A. Aleisa, “Enhancing Security in CPS Industry 5.0 using Lightweight MobileNetV3 with Adaptive Optimization Technique,” Sci. Rep., vol. 15, no. 1, p. 18677, May 2025, doi: 10.1038/s41598-025-00496-3.
X. Liang, J. Liang, T. Yin, and X. Tang, “A lightweight method for face expression recognition based on improved MobileNetV3,” IET Image Process., vol. 17, no. 8, pp. 2375–2384, Jun. 2023, doi: 10.1049/ipr2.12798.
F. Guo, W. Susilo, and Y. Mu, “Distance-Based Encryption: How to Embed Fuzziness in Biometric-Based Encryption,” IEEE Trans. Inf. Forensics Secur., vol. 11, no. 2, pp. 247–257, Feb. 2016, doi: 10.1109/TIFS.2015.2489179.
L. Laishram, M. Shaheryar, J. T. Lee, and S. K. Jung, “Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and Solutions,” ACM Comput. Surv., vol. 57, no. 6, pp. 1–38, Jun. 2025, doi: 10.1145/3673224.
Q. Ren, C. Yuan, Y. Zhao, and L. Yang, “A novel metric learning framework by exploiting global and local information,” Neuro-computing, vol. 507, pp. 84–96, Oct. 2022, doi: 10.1016/j.neucom.2022.08.003.
V. Bazarevsky, Y. Kartynnik, A. Vakunov, K. Raveendran, and M. Grundmann, “BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs,” ArXiv. Jul. 14, 2019.
J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, “RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020, pp. 5202–5211. doi: 10.1109/CVPR42600.2020.00525.
K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, “Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks,” IEEE Signal Process. Lett., vol. 23, no. 10, pp. 1499–1503, Oct. 2016, doi: 10.1109/LSP.2016.2603342.
S. Chen, Y. Liu, X. Gao, and Z. Han, “MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile De-vices,” 2018, pp. 428–438. doi: 10.1007/978-3-319-97909-0_46.
Y. Martindez-Diaz, L. S. Luevano, H. Mendez-Vazquez, M. Nicolas-Diaz, L. Chang, and M. Gonzalez-Mendoza, “ShuffleFaceNet: A Lightweight Face Architecture for Efficient and Highly-Accurate Face Recognition,” in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Oct. 2019, pp. 2721–2728. doi: 10.1109/ICCVW.2019.00333.
F. Olweny, “Navigating the nexus of security and privacy in modern financial technologies,” GSC Adv. Res. Rev., vol. 18, no. 2, pp. 167–197, Feb. 2024, doi: 10.30574/gscarr.2024.18.2.0043.
D. Aguilar, A. Martínez-Cruz, K. A. Ramírez-Gutiérrez, and M. Morales-Sandoval, “PPG-based biometric authentication: A review on architectures, datasets, attacks and security challenges,” Comput. Struct. Biotechnol. J., vol. 28, pp. 511–528, Jan. 2025, doi: 10.1016/j.csbj.2025.11.006.
W. Yang, S. Wang, N. M. Sahri, N. M. Karie, M. Ahmed, and C. Valli, “Biometrics for Internet-of-Things Security: A Review,” Sensors, vol. 21, no. 18, p. 6163, Sep. 2021, doi: 10.3390/s21186163.
V. Schlatt, J. Sedlmeir, S. Feulner, and N. Urbach, “Designing a Framework for Digital KYC Processes Built on Blockchain-Based Self-Sovereign Identity,” Inf. Manag., vol. 59, no. 7, p. 103553, Nov. 2022, doi: 10.1016/j.im.2021.103553.
S. S. U. Hasan, A. Ghani, A. Daud, H. Akbar, and M. F. Khan, “A Review on Secure Authentication Mechanisms for Mobile Se-curity,” Sensors, vol. 25, no. 3, p. 700, Jan. 2025, doi: 10.3390/s25030700.
Q. N. Tran, B. P. Turnbull, H.-T. Wu, A. J. S. de Silva, K. Kormusheva, and J. Hu, “A Survey on Privacy-Preserving Blockchain Systems (PPBS) and a Novel PPBS-Based Framework for Smart Agriculture,” IEEE Open J. Comput. Soc., vol. 2, pp. 72–84, 2021, doi: 10.1109/OJCS.2021.3053032.
S. Sharma and R. Dwivedi, “A survey on blockchain deployment for biometric systems,” IET Blockchain, vol. 4, no. 2, pp. 124–151, Jun. 2024, doi: 10.1049/blc2.12063.
O. Umoren, R. Singh, Z. Pervez, and K. Dahal, “Securing Fog Computing with a Decentralised User Authentication Approach Based on Blockchain,” Sensors, vol. 22, no. 10, p. 3956, May 2022, doi: 10.3390/s22103956.
A. Alharthi, Q. Ni, and R. Jiang, “A Privacy-Preservation Framework Based on Biometrics Blockchain (BBC) to Prevent Attacks in VANET,” IEEE Access, vol. 9, pp. 87299–87309, 2021, doi: 10.1109/ACCESS.2021.3086225.
N. Zeeshan, M. Bakyt, N. Moradpoor, and L. La Spada, “Continuous Authentication in Resource-Constrained Devices via Biometric and Environmental Fusion,” Sensors, vol. 25, no. 18, p. 5711, Sep. 2025, doi: 10.3390/s25185711.
P. Grother, M. Ngan, and K. Hanaoka, “Face recognition vendor test part 3: Demographic effects,” Gaithersburg, MD, Dec. 2019. doi: 10.6028/NIST.IR.8280.
J. Buolamwini and T. Gebru, “Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification,” in Pro-ceedings of the 1st Conference on Fairness, Accountability and Transparency, 2018, vol. 81, pp. 77–91. [Online]. Available: https://proceedings.mlr.press/v81/buolamwini18a.html
S. Vadim, M. Firdaus, and K.-H. Rhee, “Privacy-Preserving Decentralized Biometric Identity Verification in Car-Sharing System,” J. Multimed. Inf. Syst., vol. 11, no. 1, pp. 17–34, Mar. 2024, doi: 10.33851/JMIS.2024.11.1.17.
X. Zhu and C. Cao, “Secure Online Examination with Biometric Authentication and Blockchain-Based Framework,” Math. Probl. Eng., vol. 2021, pp. 1–12, Aug. 2021, doi: 10.1155/2021/5058780.
J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019, pp. 4685–4694. doi: 10.1109/CVPR.2019.00482.
S. Sengupta, J.-C. Chen, C. Castillo, V. M. Patel, R. Chellappa, and D. W. Jacobs, “Frontal to profile face verification in the wild,” in 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Mar. 2016, pp. 1–9. doi: 10.1109/WACV.2016.7477558.
S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou, “AgeDB: The First Manually Collected, In-the-Wild Age Database,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jul. 2017, pp. 1997–2005. doi: 10.1109/CVPRW.2017.250.
A. Kanak et al., “Integrated secure distance bounding and hardware-based security: A case study for the insurance claim verification of farmers during COVID-19,” Open Res. Eur., vol. 3, p. 40, Feb. 2023, doi: 10.12688/openreseurope.15448.1.
M. Y. Hong, K. H. Lee, J. H. Jung, and J. W. Yoon, “ToMAS: Torus-based secure multi-factor biometric authentication system,” Comput. Struct. Biotechnol. J., vol. 28, pp. 529–537, Jan. 2025, doi: 10.1016/j.csbj.2025.10.042.
K. Velayuthapandian, N. Murugan, and S. Paramasivan, “End-to-End CNN conceptual model for a biometric authentication mechanism for ATM machines,” Discov. Electron., vol. 1, no. 1, p. 26, Nov. 2024, doi: 10.1007/s44291-024-00034-x.
L. Nosrati, A. M. Bidgoli, and H. H. S. Javadi, “Identifying People’s Faces in Smart Banking Systems Using Artificial Neural Net-works,” Int. J. Comput. Intell. Syst., vol. 17, no. 1, p. 9, Jan. 2024, doi: 10.1007/s44196-023-00383-7.
Purnawansyah, A. P. Wibawa, T. Widyaningtyas, Haviluddin, H. Darwis, H. Azis, and Z. Ali, “Indonesian Muslim Student Face Dataset (IMSFD),” Mendeley Data, V1, 2023, doi: 10.17632/f6f3y6ndgw.1.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Dendy K. Pramudito, Jufriadif Na'am, Ferda Ernawan
This work is licensed under a Creative Commons Attribution 4.0 International License.
