Volume 21 • Issue 2 • PP: 119-148 • 2026
GLU-Attention Hybrid Architecture for Dual-Biometric Passkey Generation via Neuro-Symbolic and Chaotic Dynamics
Open Access & Copyright
© 2026 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
View PDF Abstract
The generation of cryptographic keys from biometric traits presents an opportunity to replace traditional password-based systems with mechanisms grounded in individual physiology. Nonetheless, reliably deriving secure and reproducible keys from modalities such as fingerprints and irises remains a significant challenge, particularly under varying input conditions and constraints on entropy. In this work, we present a hybrid dual-path deep learning architecture that combines Gated Linear Units (GLUs) with Squeeze-and-Excitation (SE) modules to extract rich, multimodal embeddings from iris and fingerprint images. The model, trained on an augmented cross-modal dataset, achieved a test accuracy of 99.92% and consistently high F1-scores across 50 subjects. To derive the cryptographic key, we apply a multi-stage pipeline that blends principal component projections, distance-based feature encoding, chaotic sequence modeling based on Lorenz-like dynamics, and a lightweight error-correcting routine. These representations are fused via a custom mixing function, producing a 512-bit binary vector subsequently refined using a SHA-256-based HKDF. Evaluation of the generated keys indicates near-ideal entropy, high inter-user separation, and strong avalanche characteristics. The system also passed multiple NIST statistical randomness tests and achieved a near-zero false acceptance rate. These results support the feasibility of the proposed method for secure and repeatable biometric key generation.
Keywords
References
[1] F. Corella, “Overcoming the UX challenges faced by FIDO credentials in the consumer space,” in Proc. Lect. Notes Comput. Sci., 2023, doi: 10.1007/978-3-031-35822-7_30.
[2] J. M. - and G. B. K. -, “Detection of fake biometrics - assessment of image quality in face, fingerprint,” Int. J. Multidiscipl. Res., vol. 6, no. 1, 2024, doi: 10.36948/ijfmr.2024.v06i01.12063.
[3] K. Yasunaga and K. Yuzawa, “On the limitations of computational fuzzy extractors,” IEICE Trans. Fundamentals Electron., Commun. Comput. Sci., vol. E106A, no. 3, 2023, doi: 10.1587/transfun.2022CIL0001.
[4] Mehmood, A. Shafique, M. Alawida, and A. N. Khan, “Advances and vulnerabilities in modern cryptographic techniques: A comprehensive survey on cybersecurity in the domain of machine/deep learning and quantum techniques,” IEEE Access, vol. 12, 2024, doi: 10.1109/ACCESS.2024.3367232.
[5] S. A. El-Rahman and A. S. Alluhaidan, “Enhanced multimodal biometric recognition systems based on deep learning and traditional methods in smart environments,” PLoS One, vol. 19, no. 2, 2024, doi: 10.1371/journal.pone.0291084.
[6] P. Dash, F. Pandey, M. Sarma, and D. Samanta, “Efficient private key generation from iris data for privacy and security applications,” J. Inf. Secur. Appl., vol. 75, 2023, doi: 10.1016/j.jisa.2023.103506.
[7] A. AbdulRaheeM and S. A. Hasso, “Generate and evaluate encryption keys obtained from iris biometric data,” in *Proc. 21st Int. Multi-Conf. Syst., Signals Devices (SSD)*, Apr. 2024, pp. 321–328, doi: 10.1109/SSD61670.2024.10548985.
[8] L. Chao, T. Nazaré, and E. Nepomuceno, “Key generation from fingerprint biometric,” in Proc. 15th IEEE Int. Conf. Ind. Appl. (INDUSCON), Nov. 2023, pp. 611–612, doi: 10.1109/INDUSCON58041.2023.10374712.
[9] Z. I. A. Al-Rifaee, T. Z. Ismaeel, and S. I. Abood, “Cryptography based on fingerprint bio metrics,” J. Internet Serv. Inf. Secur., vol. 14, no. 4, pp. 401–417, Nov. 2024, doi: 10.58346/JISIS.2024.I4.025.
[10] P. Dash, M. Sarma, and D. Samanta, “Fractal-based approach to secure key generation from fingerprint and iris biometrics,” in Proc. Lect. Notes Comput. Sci., 2024, pp. 99–111, doi: 10.1007/978-3-031-58181-6_9.
[11] D. K. Vallabhadas and M. Sandhya, “Cancelable bimodal shell using fingerprint and iris,” J. Electron. Imaging, vol. 32, no. 6, Dec. 2023, doi: 10.1117/1.JEI.32.6.063027.
[12] B. Wang et al., “High-security dual-image encryption based on fingerprint key with strong robustness,” Optik, vol. 288, p. 171245, Oct. 2023, doi: 10.1016/j.ijleo.2023.171245.
[13] R. Sridevi and P. Shobana, “Multimodal security of iris and fingerprint with bloom filters,” arXiv, Jun. 2024.
[14] K. N. Singh, N. Baranwal, O. P. Singh, and A. K. Singh, “DeepENC: Deep learning-based ROI selection for encryption of medical images through key generation with multimodal information fusion,” IEEE Trans. Consum. Electron., vol. 70, no. 3, pp. 6149–6156, Aug. 2024, doi: 10.1109/TCE.2024.3406963.
[15] B. Wang et al., “A multiple-image encryption method based on bimodal biometric keys,” Opt. Commun., vol. 565, p. 130651, Aug. 2024, doi: 10.1016/j.optcom.2024.130651.
[16] J. Muhammad, Y. Wang, J. Hu, K. Zhang, and Z. Sun, “CASIA-Iris-Africa: A large-scale African iris image database,” Mach. Intell. Res., vol. 21, no. 2, 2024, doi: 10.1007/s11633-022-1402-8.
[17] N. K. Sreeja, “A hierarchical heterogeneous ant colony optimization based fingerprint recognition system,” Intell. Syst. Appl., vol. 17, 2023, doi: 10.1016/j.iswa.2023.200180.
[18] J. Ren, C. Li, Y. An, W. Zhang, and C. Sun, “Few-shot fine-grained image classification: A comprehensive review,” AI, vol. 5, no. 1, 2024, doi: 10.3390/ai5010020.
[19] C. Liu, J. Zhen, and W. Shan, “Time series classification based on convolutional network with a gated linear units kernel,” Eng. Appl. Artif. Intell., vol. 123, 2023, doi: 10.1016/j.engappai.2023.106296.
[20] T. Kumar, S. Bhushan, and S. Jangra, “Ann trained and WOA optimized feature-level fusion of iris and fingerprint,” Mater. Today Proc., vol. 51, pp. 1–11, 2022, doi: 10.1016/j.matpr.2021.03.604.
[21] C. Kamlaskar and A. Abhyankar, “Iris-fingerprint multimodal biometric system based on optimal feature level fusion model,” AIMS Electron. Electr. Eng., vol. 5, no. 4, pp. 229–250, 2021, doi: 10.3934/electreng.2021013.
[22] Jagadeesan and K. Duraiswamy, “Secured cryptographic key generation from multimodal biometrics: Feature level fusion of fingerprint and iris,” Int. J. Comput. Sci. Inf. Secur., vol. 7, no. 1, 2010.
[23] Almomani et al., “Proposed biometric security system based on deep learning and chaos algorithms,” Comput., Mater. Contin., vol. 74, no. 2, pp. 3515–3537, 2023, doi: 10.32604/cmc.2023.033765.
[24] T. G. Yirga, H. G. Yirga, and E. G. Addisu, “Cryptographic key generation using deep learning with biometric face and finger vein data,” Front. Artif. Intell., vol. 8, Apr. 2025, doi: 10.3389/frai.2025.1545946.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.