An efficient CNN guided adaptive Rubik cube image encryption scheme

Mankar, Prajakta Vijay; Gode, Ruchi Telang; Murthy, S. V. S. S. N. V. G. Krishna

doi:10.47974/JDMSC-2761

Open Access Research Article

An efficient CNN guided adaptive Rubik cube image encryption scheme

Prajakta Vijay Mankarprajaktamankar8944@gmail.comDepartment of Applied MathematicsDefence Institute of Advanced Technology (Deemed to be University)Pune, Maharashtra, 411025, IndiaView full profile → , ^*Ruchi Telang GodeCorresponding authortelang.ruchi82@gmail.comDepartment of MathematicsNational Defence Academy (NDA)Pune, Maharashtra, 411023, IndiaView full profile → , S. V. S. S. N. V. G. Krishna Murthysgkmurthy@gmail.comDepartment of Applied MathematicsDefence Institute of Advanced Technology (Deemed to be University)Pune, Maharashtra, 411025, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 2521–2533Vol. 29Issue 6June 2026DOI: 10.47974/JDMSC-2761 Crossmark XML

Received:: 01 Mar 2026
Published Online:: 13 Jun 2026
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2761
Pages:: 2521–2533

Abstract

In this work, we introduce a new method for image encryption that improves on the traditional Rubik cube based encryption model by integrating adaptive key generation using Convolutional Neural Networks (CNN) and Pseudo Random Number Generator (PRNG). Chaotic masking with Rubik cube based pixel permutation was employed in while effective, these masking employ static or random key vectors that are independent of the image content. This paper demonstrates that deep learning (CNN) guided adaptive key generation, coupled with robust permutation-diffusion architecture and non-chaotic (PRNG) masking, can deliver outstanding theoretical and empirical security in image encryption even without traditional chaotic maps. Our CNN guided enhancement dynamically generates permutation vectors based on image features, introducing data adaptivity, larger key space, and enhanced security. This approach opens avenues for secure multimedia protection leveraging the frontier of AI driven cryptography and also reduces the time complexity. The proposed system achieves near ideal entropy, superior NPCR/UACI ratios, and high resilience to differential and statistical attacks while preserving computing efficiency suitable for real time systems. Experimental validation exhibits improvement over previous works in many instances.

Keywords

Image encryption Rubik cube Pseudo random number generator Convolution neural network Statistical analysis Differential attack

Subject Classifications

94A6068P2568T07

References

[1] L. Xu, Y. Chen, Y. Qin, and Z. Yang, “A mixed chaotic image encryption method based on parallel rotation scrambling in Rubik’s cube space,” Entropy, vol. 27, no. 6, p. 574 (2025), doi: 10.3390/e27060574.
[2] M. Palav, R. T. Gode, and S. V. S. S. N. V. G. Krishna Murthy, “An efficient image encryption scheme combining Rubik’s cube principle with masking,” in Neural Networks, Machine Learning, and Image Processing. Boca Raton, FL, USA: CRC Press (Taylor & Francis), pp. 181–198 (2022).
[3] S. Sharmila, R. S. Bhuvaneswaran, and D. Vaithiyanathan, “Secure image encryption using Rubik’s cube-based scrambling with chaos-driven diffusion and circular shifts,” Optik, vol. 339 (2025), doi: 10.1016/j.ijleo.2025.172533.
[4] C. S. Joice, S. H. Shanthini, K. Harsha, and S. Gopika, “A comprehensive review of image encryption algorithms: Techniques and applications,” in Proc. 5th Int. Conf. Data Intelligence and Cognitive Informatics (ICDICI), Tirunelveli, India, pp. 920–926 (2024), doi: 10.1109/ICDICI62993.2024.10810878.
[5] A. S. Sajitha and A. Shobha Rekh, “Review on various image encryption schemes,” Materials Today: Proceedings, vol. 58, no. 1, pp. 529–534 (2022), doi: 10.1016/j.matpr.2022.03.058.
[6] N. Tufillaro, “Nonlinear and chaotic string vibrations,” American Journal of Physics, vol. 57, no. 5, pp. 408–414 (1989).
[7] M. Palav, R. T. Gode, and S. V. S. S. N. V. G. Krishna Murthy, “A masking-based image encryption scheme using chaotic map and elliptic curve cryptography,” in Mathematical Modeling, Computational Intelligence Techniques and Renewable Energy, vol. 1287, Advances in Intelligent Systems and Computing, Singapore: Springer, pp. 131–145 (2021).
[8] S. Zhu and C. Zhu, “Secure image encryption algorithm based on hyperchaos and dynamic DNA coding,” Entropy, vol. 22, no. 7, p. 772 (2020), doi: 10.3390/e22070772.
[9] W. Hu, R. Zhou, S. Jiang, and G. Luo, “Quantum image encryption algorithm based on Arnold scrambling and wavelet transforms,” Quantum Information Processing, vol. 19, no. 3, pp. 1–29 (2020).
[10] J. Zhou, J. Li, and X. Di, “A novel lossless medical image encryption scheme based on game theory with optimized ROI parameters and hidden ROI position,” IEEE Access, vol. 8, pp. 122210–122228 (2020), doi: 10.1109/ACCESS.2020.3007550.
[11] M. Kaur and V. Kumar, “Comprehensive review on image encryption techniques,” Archives of Computational Methods in Engineering, vol. 27, no. 1, pp. 15–43 (2020), doi: 10.1007/s11831-018-9298-8.
[12] K. O’Shea and R. Nash, “An introduction to convolutional neural networks,” arXiv preprint arXiv:1511.08458, (Nov. 2015). [Online]. Available: https://arxiv.org/abs/1511.08458.
[13] V. Kaur, D. P. Bhatt, P. K. Tiwari, and S. Tharewal, “Blockchain technology combined with the CNN and hashing algorithms enabled the secure storage of 3D biometric face and ear data,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 26, no. 3, pp. 729–738 (2023), doi: 10.47974/JDMSC-1745.
[14] K. Fukushima, S. Miyake, and T. Ito, “Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 13, no. 5, pp. 826–834 (Oct. 1983).
[15] S. N. Bhagirath, V. Bhatnagar, and L. Raja, “A comparative analysis of optimized CNN models using bio-inspired algorithms,” Journal of Information and Optimization Sciences, vol. 46, no. 2, pp. 531–540 (2025), doi: 10.47974/JIOS-1957.
[16] B. Zhang and L. Liu, “Chaos-based image encryption: Review, application, and challenges,” Mathematics, vol. 11, no. 11 (2021), doi: 10.3390/math11112585.
[17] Z. Man, J. Li, X. Di, Y. Sheng, and Z. Liu, “Double image encryption algorithm based on neural network and chaos,” Chaos, Solitons & Fractals, vol. 152 (2021), doi: 10.1016/j.chaos.2021.111318.
[18] Y. Ding, G. Wu, D. Chen, N. Zhang, L. Gong, and M. Cao, “A deep-learning-based image encryption and decryption network for Internet of Medical Things,” IEEE Internet of Things Journal, vol. 8, no. 3, pp. 1504–1518 (Feb. 2021).
[19] S. Kumaran, R. Aarthi V. Arthi, and G. Hemalatha, “Image encryption using convolutional neural network,” ITM Web of Conferences, vol. 56 (2023), doi: 10.1051/itmconf/20235605005.
[20] L. Pasqualini and M. Parton, “Pseudo random number generation: A reinforcement learning approach,” Procedia Computer Science, vol. 170, pp. 1122–1127 (2020), doi: 10.1016/j.procs.2020.03.057.

Views: 117Downloads: 96Citations: 0