Secure Image Reconstruction using Deep Learning-based Autoencoder with Integrated Encryption Layers

Wurood Abd Ali

doi:10.31185/wjcms.316

Authors

Wurood Abd Ali Department of Computer Techniques Engineering, Alsafwa University College

DOI:

https://doi.org/10.31185/wjcms.316

Keywords:

Autoencoder (AE), Convolutional neural network (CNN), Bidirectional gated recurrent neural network (BiGRU), Deep learning (DL)

Abstract

This study presents an autoencoder model designed for secure image reconstruction through the integration of encryption and decryption layers within its framework. The major goal is to achieve more effective image reconstruction while safeguarding data integrity. A convolutional neural network (CNN) is first utilized as the primary architecture, attaining a reconstruction accuracy of 90.63% with 2.3737x losses. This brought an opportunity for further improvement, and thus we propose the improved model with the integration of CNN and bidirectional gated recurrent unit (BiGRU) as hybrid model. The integration of CNN-BiGRU leverages the feature extraction advantage of CNN and the temporal processing ability of BiGRU to a great improvement of reconstruction accuracy, reaching 95.57% and validation accuracy stabilizing around 0.85 at the end of training. The model exhibits great accuracy without significant overfitting, thus acquiring robust characteristics crucial for precise image reconstruction. In this work, the hybrid model outperforms the conventional CNN-only architectures for secure image reconstruction and can thus be considered a potential approach when high fidelity with security is required in processing image data.

Downloads

Download data is not yet available.

References

L. Dai, L. Hu, L. Chen, C. Wang, and F. Lin, “An Image Double Encryption Based on Improved GAN and Hyper Chaotic System,” IEEE Access, vol. 12, pp. 135779–135798, 2024, doi: 10.1109/ACCESS.2024.3462547.

M. Abdelmalek, A. Harhoura, I. Elaloui, M. Madani, and E.-B. Bourennane, “Visually Image Encryption based on Efficient Deep Learning Autoencoder,” Academy and Industry Research Collaboration Center (AIRCC), Jun. 2024, pp. 57–64. doi: 10.5121/csit.2024.141206.

K. Panwar, A. Singh, S. Kukreja, K. K. Singh, N. Shakhovska, and A. Boichuk, “Encipher GAN: An End-to-End Color Image Encryption System Using a Deep Generative Model,” Systems, vol. 11, no. 1, Jan. 2023, doi: 10.3390/systems11010036.

R. Archana and P. S. E. Jeevaraj, “Deep learning models for digital image processing: a review,” Artif Intell Rev, vol. 57, no. 1, Jan. 2024, doi: 10.1007/s10462-023-10631-z.

S. S. Roy, C.-H. Hsu, and V. Kagita, “Deep Learning Applications in Image Analysis.”

Y. Ding et al., “DLEDNet: A Deep Learning-based Image Encryption and Decryption Network for Internet of Medical Things”, doi: 10.48550/arXiv.2004.05523.

Z. Wang, M. Qin, and Y.-K. Chen, “Learning from the CNN-based Compressed Domain,” in 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 4000–4008. doi: 10.1109/WACV51458.2022.00405.

A. M. Abbass and R. S. Fyath, “Performance investigation of geometric constellation shaping-based coherent WDM optical fiber communication system supported by deep-learning autoencoder,” Results in Optics, vol. 15, p. 100629, 2024, doi: https://doi.org/10.1016/j.rio.2024.100629.

A. M. Abbass and R. S. Fyath, “Simulation Platform for End-to-End Deep Learning Based Coherent Fiber Communication System,” in 2023 3rd International Scientific Conference of Engineering Sciences, ISCES 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 59–63. doi: 10.1109/ISCES58193.2023.10311492.

F. Hu, C. Pu, H. Gao, M. Tang, and L. Li, “An image compression and encryption scheme based on deep learning,” Aug. 2016, doi: 10.48550/arXiv.1608.05001.

T. V, N. Mantripragada, A. P. Singh, and N. Bhasin, “Encrypting Multiple Images using Stacked Autoencoders,” in 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), 2019, pp. 1–6. doi: 10.1109/ViTECoN.2019.8899495.

K. Sreelakshmi and R. V Ravi, “An Encryption-then-Compression Scheme Using Autoencoder Based Image Compression for Color Images,” in 2020 7th International Conference on Smart Structures and Systems (ICSSS), 2020, pp. 1–5. doi: 10.1109/ICSSS49621.2020.9201967.

Y. Alslman, E. Alnagi, A. Ahmad, Y. AbuHour, R. Younisse, and Q. Abu Al-haija, “Hybrid Encryption Scheme for Medical Imaging Using AutoEncoder and Advanced Encryption Standard,” Electronics (Switzerland), vol. 11, no. 23, Dec. 2022, doi: 10.3390/electronics11233967.

F. Ahmed et al., “A DNA Based Colour Image Encryption Scheme Using A Convolutional Autoencoder,” ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 19, Nov. 2022, doi: 10.1145/3570165.

A. K. Naveen, S. Thunga, A. Murki, M. A. Kalale, and S. Anil, “Autoencoded Image Compression for Secure and Fast Transmission,” Jul. 2024, [Online]. Available: http://arxiv.org/abs/2407.03990

S. Kato and K. Hotta, “MSE Loss with Outlying Label for Imbalanced Classification,” Jul. 2021, [Online]. Available: http://arxiv.org/abs/2107.02393

S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015. JMLR: W&CP volume 37.

X. Hu, Y. Huo, X. Dong, F. Y. Wu, and A. Huang, “Channel Prediction Using Adaptive Bidirectional GRU for Underwater MIMO Communications,” IEEE Internet Things J, vol. 11, no. 2, pp. 3250–3263, Jan. 2024, doi: 10.1109/JIOT.2023.3296116.

X. Yin, C. Liu, and X. Fang, “Sentiment Analysis based on BiGRU Information Enhancement,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Jan. 2021. doi: 10.1088/1742-6596/1748/3/032054.

Z. Liu, X. Liu, S. Xiao, W. Yang, and W. Hu, “Bi-GRU Enhanced Cost-Effective Memory-Aware End-to-End Learning for Geometric Constellation Shaping in Optical Coherent Communications,” IEEE Photonics J, vol. 16, no. 1, pp. 1–10, Feb. 2024, doi: 10.1109/JPHOT.2023.3344184.