Journal of Information Technology Management

Journal of Information Technology Management

Deep Learning Iris Cryptography: A Deep Learning-Based Image Encryption Framework for Secure Information Management

Document Type : Research Paper

Authors
Awadhesh Kumar Singh 1
Amrit Kumar Agrawal 2
1 Ph.D. Scholar, Department of CSE, Sharda School of Engineering & Technology, Sharda University, Greater Noida-201306 UP, India.
2 Associate Professor, Department of CSE, Sharda School of Engineering & Technology, Sharda University, Greater Noida-201306 UP, India.
10.22059/jitm.2026.108918
Abstract
As high-resolution image data increasingly becomes commonplace in healthcare, surveillance systems, smart environments, and cloud platforms, ensuring image security has become one of the major challenges of our time. In this paper, we develop DL-IrisCrypt, a novel biometric-based image encryption framework in which the ciphertext is associated with the identity of the authorized user. We extract a 2048-bit iris code using Daugman segmentation and Gabor filters, which is then used to generate a key for initializing a six-dimensional hyperchaotic system and processed through SHA-512 and HKDF. To enhance randomness in the key-generation process, we incorporate features extracted from the latent space of a properly trained U-Net autoencoder model. The encryption architecture uses Fisher-Yates permutation, two layers operating with PCG64 in counter mode, and three passes of BLAKE2b cipher-block chaining. Experimental results show that the proposed approach achieves an NPCR of 99.61%, a UACI of 33.46%, and an information entropy of 7.9966 bits/byte, while passing all randomness tests provided by NIST SP 800-22. The framework requires an average of 16 milliseconds for encryption and 188 milliseconds for end-to-end processing on a single GPU and has an effective key space of 2^512. In addition to providing robust information security, DL-IrisCrypt offers features that can benefit organizations handling sensitive visual materials. By combining biometric identification, deep learning, and lightweight encryption mechanisms, the system enables secure management and preservation of the confidentiality of important digital assets while facilitating efficient information sharing with low computational requirements.
Keywords
Deep learning
image encryption
iris biometrics
SHA-512
U-Net autoencoder
BLAKE2b-CBC
Agustsson, E., & Timofte, R. (2017). NTIRE 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 126–135).
Alvarez, G., & Li, S. (2006). Some basic cryptographic requirements for chaos-based cryptosystems. International Journal of Bifurcation and Chaos, 16(8), 2129–2151.
Amrit, P., et al. (2023). EmbedR-Net: Using CNN for secure eHealth systems. IEEE Transactions on Consumer Electronics, 69(4), 1017–1022.
Amutha, R. (2026). Chaotic image encryption using circular shift and modular arithmetic. Journal of Discrete Mathematical Sciences and Cryptography, 29(1), 215–228. https://doi.org/10.47974/JDMSC-2411
Aumasson, J.-P., Neves, S., Wilcox-O'Hearn, Z., & Winnerlein, C. (2013). BLAKE2: Simpler, smaller, fast as MD5. In Proceedings of the 11th International Conference on Applied Cryptography and Network Security (ACNS) (pp. 119–135).
Barker, E. (2020). Recommendation for key management—Part 1: General (NIST Special Publication 800-57 Part 1 Rev. 5). National Institute of Standards and Technology.
Bourekouche, H., Belkacem, S., & Messaoudi, N. (2025). Design and analysis of a PRNG based on the logistic-sine system. Journal of Discrete Mathematical Sciences and Cryptography, 28(7), 2645–2670.
Daugman, J. (2004). How iris recognition works. IEEE Transactions on Circuits and Systems for Video Technology, 14(1), 21–30.
Daugman, J. (2006). Probing the uniqueness and randomness of IrisCodes. Proceedings of the IEEE, 94(11), 1927–1935.
Fridrich, J. (1998). Symmetric ciphers based on two-dimensional chaotic maps. International Journal of Bifurcation and Chaos, 8(6), 1259–1284.
Huang, X., Ye, Y., Dai, S., & Zhang, Y. (2023). Image encryption scheme using chaotic map and pixel-level diffusion with S-box substitution. Mathematics, 11(4), Article 866. https://doi.org/10.3390/math11040866
ISO/IEC. (2022). Information security, cybersecurity and privacy protection—Information security management systems—Requirements (ISO/IEC 27001:2022). International Organization for Standardization.
Jain, A. K., Nandakumar, K., & Nagar, A. (2008). Biometric template security. EURASIP Journal on Advances in Signal Processing, 2008, Article 579416.
Jyotsna, L., & Kumar, L. P. (2026). Enhanced image security through block permutation. Journal of Discrete Mathematical Sciences and Cryptography, 29(3), 1313–1333.
Krawczyk, H., & Eronen, P. (2010). HMAC-based extract-and-expand key derivation function (HKDF) (RFC 5869). Internet Engineering Task Force.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.
Rohhila, S., & Singh, A. K. (2024). Deep learning-based encryption for secure digital images: A survey. Computers & Electrical Engineering, 116, Article 109236.
Rohhila, S., Singh, K. N., Singh, A. K., & Gupta, B. B. (2025). DeepKey-TPE: Using deep learning to generate key for image security with continued usability through thumbnail-preserving encryption. IEEE Transactions on Consumer Electronics. Advance online publication. https://doi.org/10.1109/TCE.2025.3605213
Singh, A. K., & Agrawal, A. K. (2026). HybridCrypt-AE: A deep learning–augmented hyperchaotic image encryption scheme with dual-feedback diffusion and SHA-512 key generation. Journal of Discrete Mathematical Sciences and Cryptography.
Stallings, W. (2023). Cryptography and network security (8th ed.). Pearson.
Wang, X., & Liu, C. (2017). A novel and effective image encryption algorithm based on chaos and DNA encoding. Multimedia Tools and Applications, 76(5), 6229–6245. https://doi.org/10.1007/s11042-016-3311-8
Journal of Information Technology Management
Volume 18, Issue 4
2026
Pages 117-133