HybridCrypt-AE : A deep learning–augmented hyperchaotic image encryption scheme with dual-feedback diffusion and SHA-512 key generation
Awadhesh Kumar Singhawadheshcse@gmail.comDepartment of Computer Science & EngineeringSharda School of Computing Science & EngineeringSharda UniversityGreater Noida, Uttar Pradesh, 201310, IndiaView full profile → , *Amrit Kumar AgrawalCorresponding authoragrawal.amrit4@gmail.comDepartment of Computer Science & EngineeringSharda School of Computing Science & EngineeringSharda UniversityGreater Noida, Uttar Pradesh, 201310, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Jan 2026
- Published Online:
- 30 Sep 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-2857
- Pages:
- 3391–3407
Abstract
In the digital age, where consumer electronics, healthcare, surveillance, and cloud computing have significantly increased the amount of image-based data, image security has become an issue of great concern. Traditional encryption techniques are unable to provide multiple levels of security, computational efficiency, and verifiable lossless recovery. This study explains the Hybridcrypt-AE, a new image encryption method built upon a hybrid autoencoder (hybridae) to enhance deep-feature key augmentation using plainimage dependent dynamic key generation via SHA-512, dual stream PCG64 based on 6D hyperchaotic PRNG, fisherman-yates pixel permutation and three rounds of dual feedback permutation-diffusion cipher. The scheme achieves a NPCR of 99.61% , 33.45% UACI, 7.9998 bits of information entropy, 9.07 dB of PSNR, and decrypted PSNR greater than 100 % with an SSIM of 1.0. The key space is at least 63,000 times larger than all of the other methods reviewed in this paper with respect to exponent, at 2^2097664 . Encrypting a 512 x 512 file uses 0.2513 seconds while Deepkey-tpe uses 0.728 seconds to encrypt. All of the individual components have been shown to add quantitatively towards adding security with ablation studies. The comparison of the state-of-the-art shows that Hybridcrypt-ae has better security, efficiency and recovery quality.
Keywords
Subject Classifications
References
[1] S. Rohhila and A. K. Singh, “Deep learning-based encryption for secure transmission digital images: A survey,” Comput. Electr. Eng., vol. 116, Art. no. 109236 (2024), doi: 10.1016/j.compeleceng.2024.109236.
[2] Grand View Research, “Digital image processing market size, share & trends analysis report,” Grand View Research (2025). [Online]. Available: Grand View Research [Accessed: Feb. 2025].
[3] L. Jyotsna and L. P. Kumar, “Enhanced image security through block permutation and modular arithmetic shuffling,” J. Discrete Math. Sci. Cryptogr., vol. 29, no. 3, pp. 1313–1333 (2026), doi: 10.47974/JDMSC-2617.
[4] D. Kahn, The Codebreakers: The Story of Secret Writing. New York, USA: Macmillan (1967).
[5] H. Bourekouche, S. Belkacem, and N. Messaoudi, “Design and analysis of a pseudo random number generator based on the logistic-sine system and a nonlinear feedback shift register: Application to image encryption,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 7, pp. 2645–2670 (2025), doi: 10.47974/JDMSC-1847.
[6] R. Amutha, “Chaotic image encryption using circular shift and modular arithmetic,” J. Discrete Math. Sci. Cryptogr., vol. 29, no. 1, pp. 215–228 (2026), doi: 10.47974/JDMSC-2411.
[7] M. Paliwal, P. Soni, R. Kumar, A. Goyal, M. Malik, and B. Goyal, “Chaotic map-based selective image encryption via diffusion and confusion,” J. Discrete Math. Sci. Cryptogr., vol. 27, no. 2-B, pp. 763–773 (2024), doi: 10.47974/JDMSC-1953.
[8] J. Fridrich, “Symmetric ciphers based on two-dimensional chaotic maps,” Int. J. Bifurcation Chaos, vol. 8, no. 6, pp. 1259–1284 (1998), doi: 10.1142/S021812749800098X.
[9] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444 (2015), doi: 10.1038/nature14539.
[10] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, pp. 1125–1134 (2017), doi: 10.1109/CVPR.2017.632.
[11] S. Rohhila, K. N. Singh, A. K. Singh, and B. B. Gupta, “DeepKey-TPE: Using deep learning to generate key for image security with continued usability through thumbnail-preserving encryption,” IEEE Trans. Consum. Electron., vol. 71 (2025), doi: 10.1109/TCE.2025.3605213.
[12] L. Kocarev and S. Lian, Eds., Chaos-Based Cryptography: Theory, Algorithms and Applications. Berlin, Germany: Springer (2011).
[13] G. Alvarez and S. Li, “Some basic cryptographic requirements for chaos-based cryptosystems,” Int. J. Bifurcation Chaos, vol. 16, no. 8, pp. 2129–2151 (2006), doi: 10.1142/S0218127406016224.
[14] X. Wang and C. Liu, “A novel and effective image encryption algorithm based on chaos and DNA encoding,” Multimed. Tools Appl., vol. 76, no. 5, pp. 6229–6245 (2017), doi: 10.1007/s11042-016-3311-8.
[15] M. Matsumoto and T. Nishimura, “Mersenne twister: A 623-dimensionally equidistributed uniform pseudo-random number generator,” ACM Trans. Model. Comput. Simul., vol. 8, no. 1, pp. 3–30 (1998), doi: 10.1145/272991.272995.
[16] X. Huang, G. Ye, K. Jafari, and H. Dong, “Image encryption scheme using chaotic map and pixel-level diffusion with S-Box substitution,” Mathematics, vol. 11, no. 4, Art. no. 866 (2023), doi: 10.3390/math11040866.
[17] S. Mewada, P. Sharma, and S. Gautam, “SHA-256-seeded image encryption with chaotic maps for cloud storage,” Secur. Commun. Netw., vol. 2021, Art. no. 9963025 (2021), doi: 10.1155/2021/9963025.
[18] C. Aguilar-Melchor, P.-L. Cayrel, P. Gaborit, and F. Laguillaumie, “SHA-512 key expansion for image encryption,” Cryptogr. Commun., vol. 12, no. 3, pp. 415–436 (2020).
[19] M. Singh, N. Baranwal, K. N. Singh, and A. K. Singh, “Using GAN-based encryption to secure digital images with reconstruction through customized super resolution network,” IEEE Trans. Consum. Electron., vol. 70, no. 1, pp. 3977–3984 (2024), doi: 10.1109/TCE.2023.3285626.
[20] B. Wang and K.-T. Lo, “Autoencoder-based joint image compression and encryption,” J. Inf. Secur. Appl., vol. 80, Art. no. 103680 (2024), doi: 10.1016/j.jisa.2023.103680.
[21] A. Z. Abbasi, A. Rafiq, B. M. Alshammari, and I. H. Jaghdam, “Advanced image encryption scheme based on generalized triangle group and neural networks,” Ain Shams Eng. J., vol. 16, no. 8, Art. no. 103488 (2025), doi: 10.1016/j.asej.2025.103488.
[22] E. Barker, “Recommendation for key management: Part 1—General,” NIST Special Publication 800-57 Part 1, Rev. 5, National Institute of Standards and Technology, Gaithersburg, MD, USA (2020), doi: 10.6028/NIST.SP.800-57pt1r5.
[23] P. Amrit, A. K. Singh, M. P. Singh, and A. K. Agrawal, “EmbedR-Net: Using CNN to embed mark with recovery through deep convolutional GAN for secure eHealth systems,” IEEE Trans. Consum. Electron., vol. 69, no. 4, pp. 1017–1022 (2023), doi: 10.1109/TCE.2023.3283284.
