DEEP AUTOENCODERS FOR INFORMATION HIDDEN: MODERN APPROACHES AND DEVELOPMENT PROSPECTS
DOI:
https://doi.org/10.28925/2663-4023.2025.28.765Keywords:
deep autoencoders, steganography, information security, deep learning, neural networksAbstract
This article considers the possibilities of using deep autoencoders in the field of information hiding (steganography). It is shown that the combination of steganography methods with deep learning allows to increase the reliability of the system and increase the bandwidth of the hidden data transmission channel. A comparative review of modern autoencoder architectures is carried out, the principles of encoding and decoding are analyzed, and the generalized results of experimental studies are presented, demonstrating the effectiveness of the proposed approaches. The prospects for the development of this area are assessed in terms of security, efficiency and resistance to attacks through a detailed analysis of potential vulnerabilities and scenarios of practical implementation. The results of the study indicate the significant potential of deep autoencoders in the field of information security, in particular for integration with steganographic methods. A number of recommendations are proposed for further improvement of the technology, including optimization of the architecture of neural networks, expansion of the scope of applications and consideration of ethical and legal aspects.
Downloads
References
Bender, W., Gruhl, D., Morimoto, N., & Lu, A. (1996). Techniques for data hiding. IBM Systems Journal, 35(3–4), 313–336. https://doi.org/10.1147/sj.353.0313
Cox, I. J., Miller, M. L., Bloom, J. A., Fridrich, J., & Kalker, T. (2008). Digital watermarking and steganography. Morgan Kaufmann.
Johnson, N. F., & Katzenbeisser, S. (1998). A survey of steganographic techniques. In Information hidingб 43–78. Springer.
Zhu, J., Kaplan, R., Johnson, J., & Fei-Fei, L. (2018). HiDDeN: Hiding data with deep networks. Advances in Neural Information Processing Systems, 31.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507. https://doi.org/10.1126/science.1127647
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P. A. (2008). Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, 1096–1103. https://doi.org/10.1145/1390156.1390294
Zhou, C., & Paffenroth, R. (2017). Anomaly detection with robust deep autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 665–674. https://doi.org/10.1145/3097983.3098052
Hayes, J., & Danezis, G. (2017). Generating steganographic images via adversarial training. Advances in Neural Information Processing Systems, 30.
Montgomery, D. C. (2017). Design and Analysis of Experiments. John Wiley & Sons.
Gupta, S., Joshi, R. C., & Misra, M. A. (2019). SeGAN: Segment-based image steganography using generative adversarial network. IET Image Processing, 13(10), 1706–1713. https://doi.org/10.1049/iet-ipr.2018.6233
Lu, X., Li, B., & Huang, J. (2019). GAN-based image steganography: review and research trends. IEEE Access, 7, 179097–179110. https://doi.org/10.1109/ACCESS.2019.2958574
Zhang, R., Wang, S., & Wang, L. (2021). Robust deep steganography with pixelwise adversarial training. Neural Computing and Applications, 33, 2357–2369. https://doi.org/10.1007/s00521-020-05047-2
Hinton, G. E. (2012). A practical guide to training restricted Boltzmann machines. In Neural Networks: Tricks of the Trade (pp. 599–619). Springer. https://doi.org/10.1007/978-3-642-35289-8_32
Fridrich, J. (2009). Steganography in digital media: principles, algorithms, and applications. Cambridge University Press.
Provos, N., & Honeyman, P. (2003). Hide and seek: An introduction to steganography. IEEE Security & Privacy, 1(3), 32–44. https://doi.org/10.1109/MSECP.2003.1203220
Nissar, A. U., & Mir, A. H. (2010). Classification of steganalysis techniques: A study. Digital Signal Processing, 20(6), 1758–1770. https://doi.org/10.1016/j.dsp.2010.01.017
Li, B., Luo, X., Liu, T., & Huang, J. (2011). A survey on image steganography and steganalysis. Journal of Information Hiding and Multimedia Signal Processing, 2(2), 142–172.
Ker, A. D. (2005). Steganalysis of LSB matching in grayscale images. IEEE Signal Processing Letters, 12(6), 441–444. https://doi.org/10.1109/LSP.2005.847889
Kessler, G. C. (2010). Steganography: Encoders/decoders. In Handbook of Information Security, 1, 14–23. Wiley.
Petitcolas, F. A. P., Anderson, R. J., & Kuhn, M. G. (1999). Information hiding - a survey. Proceedings of the IEEE, 87(7), 1062–1078. https://doi.org/10.1109/5.771065
Reddy, A., Acharya, N., & Mandal, J. K. (2018). A new approach to transform domain-based robust steganography using wavelet families. Arabian Journal for Science and Engineering, 43, 5079–5090. https://doi.org/10.1007/s13369-018-3205-0
Ye, J., Ni, Z., & Ni, R. (2018). Deep embedding in DCT domain for image steganography. Proceedings of ICIP, 2336–2340. https://doi.org/10.1109/ICIP.2018.8451402
Liu, Z., Su, Z., Hou, D., & Li, H. (2018). A robust CNN-based method for image steganography and steganalysis. Multimedia Tools and Applications, 77, 21769–21785. https://doi.org/10.1007/s11042-018-6089-1
Tang, S., & Wu, X. (2020). Adaptive steganography based on deep reinforcement learning. Neurocomputing, 370, 35–46. https://doi.org/10.1016/j.neucom.2019.08.090
Yu, W., & Chen, S. (2021). Improved autoencoder-based image steganography. IEEE Access, 9, 41395–41406. https://doi.org/10.1109/ACCESS.2021.3064091
Duan, Y., Yang, B., & Gao, H. (2021). Deep hiding in video frames with convolutional neural networks. Information Sciences, 551, 27–43. https://doi.org/10.1016/j.ins.2020.11.038
Ullah, H., Mohammed, N., & Rahman, M. A. (2022). Hybrid data hiding approach for color images using deep autoencoder. Computers & Security, 114, 102589. https://doi.org/10.1016/j.cose.2021.102589
Singh, K., & Singh, B. (2022). Implementation of robust image steganography using deep autoencoders. Future Generation Computer Systems, 136, 60–72. https://doi.org/10.1016/j.future.2022.06.004
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Дмитро Прокопович-Ткаченко
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
