A Complete On-Device RGB–IR Face Presentation Attack Detection System with Independent ISO/IEC 30107-3 PAD Level 1 and Level 2 Evaluation by BixeLab
Main Article Content
Abstract
Face presentation attack detection (PAD) systems intended for real-world access control must provide not only accurate spoof detection but also reliable on-device operation, multi-sensor integration, traceable decision making, and reproducible evaluation. This paperpresentsacompleteon-deviceRGB–IRfacePADsystemimplementedonacustomAndroidaccess-control device and evaluated independently under ISO/IEC 30107-3-based test protocols. The system employs temporally paired RGB and infrared observations and integrates three complementary sources of evidence: a primary RGB liveness score, an RGB–IR cross-spectral consistency score, and a secondary independent liveness score. Frame-level outputs are combined through a
configurable transaction-level decision policy based on multi-frame aggregation, while intermediate scores, decisions, and transaction results are logged to support traceability and post-hoc analysis. The complete hardware–software system was independently evaluated by BixeLab, an ISO/IEC 17025-accredited biometric testing laboratory, at Level A and Level B. For each level, the evaluation involved 10 consenting subjects, 50 bona fide transactions, and 300 presentation attacks covering six presentation attack instrument species. No attack classification errors or attack non-responses were observed in either evaluation, corresponding to an observed APCER of 0/300 and APNRR of 0/300 at both levels. However, 10 of 50 bona fide presentations were incorrectly rejected at each level, corresponding to an observed BPCER of 20%. These results demonstrate the effectiveness of the proposed system-level integration against the evaluated attack species while also highlighting the security–usability trade-off introduced by conservative operating points. The study provides an independently validated example of a deployable and auditable RGB–IR PAD architecture for real-world biometric access-control systems.
Keywords
Android access control, Face presentation attack detection, ISO/IEC 30107-3, RGB–IR sensing
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[2] Y. Liu, A. Jourabloo, and X. Liu, Learning deep models for face anti-spoofing: Binary or auxiliary supervision, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, June 2018.
[3] Z. Yu, Y. Qin, X. Li, C. Zhao, Z. Lei, and G. Zhao, Deep learning for face anti-spoofing: A survey, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 45, no. 5, pp. 5609–5631, May 2023. https://doi.org/10.1109/TPAMI.2022.3215850
[4] S. Zhang, A. Liu, J. Wan, Y. Liang, G. Guo, S. Escalera, H. J. Escalante, and S. Z. Li, CASIA-SURF: A large-scale multi-modal benchmark for face anti-spoofing, IEEE Trans. Biometrics, Behavior, and Identity Science, vol. 2, no. 2, pp. 182–193, 2020. https://doi.org/10.1109/TBIOM.2020.2973001
[5] A. George, Z. Mostaani, D. Geissbuhler, O. Nikisins, A. Anjos, and S. Marcel, Biometric face presentation attack detection with multi-channel convolutional neural network, IEEE Trans. Information Forensics and Security, 2019.
[6] A. Liu, Z. Tan, J. Wan, S. Escalera, G. Guo, and S. Z. Li, CASIA-SURF CeFA: A benchmark for multi-modal cross-ethnicity face anti-spoofing, in Proc. IEEE/CVF Winter Conf. Applications of Computer Vision (WACV), 2021, pp. 1179–1187.
[7] Z. Yu, A. Liu, C. Zhao, K. H. M. Cheng, X. Cheng, and G. Zhao, Flexible-modal face anti-spoofing: A benchmark, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2023, pp. 6346–6351.
[8] Z. Yu, R. Cai, Y. Cui, X. Liu, Y. Hu, and A. C. Kot, Rethinking vision transformer and masked autoencoder in multimodal face anti-spoofing, International Journal of Computer Vision, vol. 132, pp. 5217–5238, 2024. https://doi.org/10.1007/s11263-024-02055-1
[9] X. Lin, S. Wang, R. Cai, Y. Liu, Y. Fu, W. Tang, Z. Yu, and A. Kot, Suppress and rebalance: Towards generalized multi-modal face anti-spoofing, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2024, pp. 211–221.
[10] J. Yang, X. Lin, Z. Yu, L. Zhang, X. Liu, H. Li, X. Yuan, and X. Cao, DADM: Dual alignment of domain and modality for face anti-spoofing, in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV), 2025, pp. 12045–12056.
[11] D. Anghelone, C. Chen, A. Ross, and A. Dantcheva, Beyond the visible: A survey on cross-spectral face recognition,
eurocomputing, vol. 611, 128626, 2025. https://doi.org/10.1016/j.neucom.2024.128626
[12] B. Hu, K. Wang, and C. H. Chang, Red bleed: A pragmatic near-infrared presentation attack on facial biometric authentication systems, in Proc. 34th USENIX Security Symposium, Seattle, WA, USA, 2025.
[13] ISO/IEC, ISO/IEC 30107-3:2023 Information Technology—Biometric Presentation Attack Detection—Part 3: Testing and Reporting, Geneva, Switzerland: International Organization for Standardization, 2023.