Citation :

Swetha Margaret TA, Divya Midhunchakkaravarthy, "AI-Driven Passwordless Authentication through MobileNetV2-Based Dynamic Password IrisCode Generation and Deep Iris Embedding Transformation," International Journal of Electronics and Communication Engineering, vol. 13, no. 8, pp. 196-211, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I8P112

Abstract

The widespread adoption of digital services, cloud infrastructure and smart access control has raised the demand for passwordless and secure authentication systems. The classic password-based authentication is susceptible to stolen credentials, phishing and replay attacks, leading to unauthorized access, whereas traditional iris authentication methods rely on fixed biometric templates with less flexibility and security. Here, proposing an AI-based passwordless authentication system using dynamic generation of Password IrisCode and iris embedding transformation. This framework utilizes a custom-designed Iris Acquisition Device with controlled lighting and a high-resolution capturing facility to secure a good-quality iris image. This captured data is then pre-processed and fed to the MobileNetV2 model to extract distinct iris features and generate compressed 128-dimension biometric features (iris embedding). Instead of traditional iris authentication using an iris feature vector, this extracted embedding is cryptographically hashed (using SHA-256) and converted to an encrypted Password IrisCode, thus securing the data while retaining the uniqueness. The proposed system authenticates the users by checking the similarity of generated iris features and the enrolled patterns. The framework is tested on a large dataset with variable illumination and acquisition conditions called CASIA-Iris-Thousand and has been able to achieve an accuracy of 95.0%, as against the accuracy of 67.09% of the IrisCode authentication system, and a failure rate has been reduced from 32.91% to 5.0%, and average processing time has been observed to be 0.4065sec for near real-time authentication. The AI-based feature extraction and the usage of dynamic Password IrisCode Generation, along with a dedicated hardware for iris acquisition, make the proposed system efficient, secure and scalable for modern passwordless access controls.

Keywords

Passwordless Authentication, Iris Recognition, MobileNetV2, Password IrisCode, Deep Learning, Biometric Security, Iris Embedding Transformation, SHA-256, Access Control, CASIA-Iris-Thousand.

References

1. Abhishek Gangwar et al., “DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition,” arXiv preprint, pp. 1-10, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
2. A. Alsubari et al., “Composite Feature Extraction and Classification for Fusion of Palm-Print and Iris Biometric Traits,” Engineering, Technology & Applied Science Research, vol. 9, no. 1, pp. 3807-3813, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Dingding Jia, and Wenzhong Shen, “Is Normalized Iris Optimal for Iris Recognition Based on Deep Learning?,” Journal of Electronic Imaging, vol. 30, no. 5, pp. 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Reihan Alinia Lat et al., “Boosting Iris Recognition by Margin-Based Loss Functions,” Algorithms, vol. 15, no. 4, pp. 1-13, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Qinhong Zou et al., “Toward More Efficient Iris Recognition Using a Lightweight CNN Framework with Attention Mechanism,” Proceedings of the International Conference on Computer Network Security and Software Engineering (CNSSE 2022), vol. 12290, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Mohammad Yamin et al., “Biometric Verification System Using Hyperparameter Tuned Deep Learning Model,” Computer Systems Science and Engineering, vol. 46, no. 1, pp. 321-336, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Lijun Zhou et al., “Iris Recognition Based on Convolutional Neural Network and Active Iterative Optimization,” 2023 International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), Dalian, China, pp. 523-528, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Dongdong Zhao et al., “Cancelable Iris Biometrics Based on Transformation Network,” 2023 IEEE 23^rd International Conference on Software Quality, Reliability, and Security (QRS), Chiang Mai, Thailand, pp. 507-516, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Shailendra W. Shende, Jitendra V. Tembhurne, and Nishat Afshan Ansari, “Deep Learning based Authentication Schemes for Smart Devices in Different Modalities: Progress, Challenges, Performance, Datasets and Future Directions,” Multimedia Tools and Applications, vol. 83, no. 28, pp. 71451-71493, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Serkan Salturk, and Nihan Kahraman, “Deep Learning-Powered Multimodal Biometric Authentication: Integrating Dynamic Signatures and Facial Data for Enhanced Online Security,” Neural Computing and Applications, vol. 36, no. 19, pp. 11311-11322, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Kien Nguyen et al., “Deep Learning for Iris Recognition: A Survey,” ACM Computing Surveys, vol. 56, no. 9, pp. 1-35, 2024.
    [CrossRef] [Publisher Link]
12. Yimin Yin et al., “Deep Learning for Iris Recognition: A Review,” Neural Computing and Applications, vol. 37, no. 17, pp. 11125-11173, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
13. K. Sivasankari, and D. Kerana Hanirex, Advancing Security on Harnessing Deep Learning for Iris Recognition and Classification, Optimizing Patient Outcomes Through Multi-Source Data Analysis in Healthcare, IGI Global Scientific Publishing, pp. 1-18, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Abdelnasser Mohammed et al., “Enhancing Network Access Control using Multi-Modal Biometric Authentication Framework,” Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20144-20150, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15.  Neama Abdulaziz Dahan, and Emad Sami Jaha, “IRIS-QResNet: A Quantum-Inspired Deep Model for Efficient Iris Biometric Identification and Authentication,” Sensors, vol. 25, no. 1, pp. 1-44, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Saif Mohanad Kadhim et al., “Deep Learning for Robust Iris Recognition: Introducing Synchronized Spatiotemporal Linear Discriminant Model-Iris,” Advances in Artificial Intelligence and Machine Learning, vol. 5, no. 1, pp. 3446-3464, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Azizur Rahman et al., “Distant Iris Recognition Through Machine Learning Models with Deep Features Transfer for Human Identification,” Journal of Innovative Image Processing, vol. 7, no. 3, pp. 840-860, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
18. J. Chethana, and J. Ravi, “Deep Segmentation Assisted Residual Spatio-Textural Ensemble Feature Learning Framework for Multimodal Person Authentication System,” International Journal of Advances in Signal and Image Sciences, vol. 12, no. 1, pp. 1011-1053, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
19. S. Alangaram et al., “AI Powered Secure Payment with Eye Recognition in Wallet Platform,” International Journal of Computer Technology and Electronics Communication, vol. 9, no. 3, pp. 1018-1025, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
20. S.V. Sheela, and K.R. Radhika, “Deep Learning Driven Fusion of Iris Biometrics for Optimised Multimodal Authentication Informative Security,” International Journal of Information and Computer Security, vol. 29, no. 4, pp. 397-435, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]