DOI: https://doi.org/10.32515/2664-262X.2025.11(42).2.79-86
Steganographic Methods in Information Security
About the Authors
Dmytro Prokopovych-Tkachenko, Associate Professor, Candidate of Technical Sciences, Head of the Department of Cyber Security and Information Technologies, University of Customs and Finance, Dnipro, Ukraine, ORCID: https://orcid.org/0000-0002-6590-3898, e-mail: omega2417@gmail.com.
Oksana Markiv, Associate Professor, PhD in Economics (Candidate of Economics Sciences), Associate Professor of the Department of Cyber Security and Information Technologies, University of Customs and Finance, Dnipro, Ukraine, ORCID: https://orcid.org/0000-0003-0413-8296, e-mail: Luda_r@ukr.net
Yaroslav Derkach, PhD student, Kharkiv National University of Radio Electronics, 14 Nauky Avenue, Kharkiv, Ukraine, ORCID: http://orcid.org/0009-0009-7208-370X, e-mail: ciscoflexx@gmail.com
Abstract
The article discusses 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 makes it possible to improve system reliability and increase the bandwidth of the hidden data transmission channel.
The purpose of this paper is to analyse modern approaches to the use of deep autoencoders in steganography, to determine their main advantages and disadvantages, and to formulate promising directions for further research. The development of deep learning opens up broad prospects for enhancing classical steganographic approaches. The use of deep neural networks allows increasing the bandwidth of the steganographic concealment channel, increase resistance to attacks, in particular, to compression, noise and other distortions and adapt to different types of media and specific security requirements will allow identifying new tools for optimising the process of information concealment. The scientific novelty lies in the combination of the ideas of steganography and deep auto-encoders, which makes it possible to obtain high quality recovery of hidden information with minimal visual, acoustic or other artefacts.
A comparative review of modern autoencoder architectures is carried out, the principles of encoding and decoding are analysed, and the results of experimental studies demonstrating the effectiveness of the proposed approaches are summarised. The prospects for the development of this area in terms of security, efficiency and resistance to attacks are assessed through a detailed analysis of potential vulnerabilities and practical implementation scenarios.
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 for further improvement of the technology are proposed, including optimisation of the neural network architecture, expansion of the scope of applications, and consideration of ethical and legal aspects.
The results of the study can be used in various areas of information security, including: digital watermarks for copyright protection; covert transmission of messages in communication channels resistant to interception; security of IoT devices, where it is important to minimise the amount of data and at the same time maintain secrecy. The methodology itself can be improved by integrating additional encryption at the level of the hidden message, which will increase the overall level of security.
Keywords
deep autoencoders, steganography, information security, deep learning, neural networks
Full Text:
PDF
References
1. Zhu J., Kaplan R., Johnson J. & Fei-Fei L. (2018). HiDDeN: Hiding data with deep networks. Advances in Neural Information Processing Systems. Vol. 31.
2. Goodfellow I., Bengio Y. & Courville A. (2016). Deep Learning. MIT Press.
3. 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. P. 665–674. http://doi.org/10.1145/3097983.3098052.
4. Hayes J. & Danezis G. (2017). Generating steganographic images via adversarial training. Advances in Neural Information Processing Systems. Vol. 30.
5. Montgomery D. C. (2017). Design and Analysis of Experiments. John Wiley & Sons.
6. Gupta S., Joshi R. C. & Misra M. A. (2019). SeGAN: Segment-based image steganography using generative adversarial network. IET Image Processing. Vol. 13, No. 10. P. 1706–1713. http://doi.org/10.1049/iet-ipr.2018.6233.
7. Lu X., Li B. & Huang J. (2019). GAN-based image steganography: review and research trends. IEEE Access. Vol. 7. P. 179097–179110. http://10.1109/ACCESS.2019.2958574.
8. Zhang R., Wang S. & Wang L. (2021). Robust deep steganography with pixelwise adversarial training. Neural Computing and Applications. Vol. 33. P. 2357–2369. http://doi.org/10.1007/s00521-020-05047-2
9. Nissar A. U. & Mir A. H. (2010). Classification of steganalysis techniques: A study. Digital Signal Processing. Vol. 20, No. 6. P. 1758–1770. http://doi.org/10.1016/j.dsp.2010.01.017.
10. Li B., Luo X., Liu T. & Huang J. (2011). A survey on image steganography and steganalysis. Journal of Information Hiding and Multimedia Signal Processing. Vol. 2, No. 2. P. 142–172.
11. Ker A. D. (2005). Steganalysis of LSB matching in grayscale images. IEEE Signal Processing Letters. Vol. 12, No. 6. P. 441–444. http://doi.org/10.1109/LSP.2005.847889.
12. Petitcolas F. A. P., Anderson R. J. & Kuhn M. G. (1999). Information hiding - a survey. Proceedings of the IEEE. Vol. 87, No. 7. P. 1062–1078. http://doi.org/10.1109/5.771065.
13. 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. Vol. 43. P. 5079–5090. http://doi.org/10.1007/s13369-018-3205-0.
14. Liu Z., Su Z. & Hou D., Li H. (2018). A robust CNN-based method for image steganography and steganalysis. Multimedia Tools and Applications. Vol. 77. P. 21769–21785. http://doi.org/10.1007/s11042-018-6089-1.
15. Tang S. & Wu X. (2020). Adaptive steganography based on deep reinforcement learning. Neurocomputing. Vol. 370. P. 35–46. http://doi.org/10.1016/j.neucom.2019.08.090.
16. Yu W. & Chen S. (2021). Improved autoencoder-based image steganography. IEEE Access. Vol. 9. P. 41395–41406. http://doi.org/10.1109/ACCESS.2021.3064091
17. Duan Y., Yang B., & Gao H. (2021). Deep hiding in video frames with convolutional neural networks // Information Sciences. Vol. 551. P. 27–43. http://doi.org/10.1016/j.ins.2020.11.038.
18. Melnyk, K.V., Melnyk, V.M., & Koptyuk, Y.Y. (2019). Research of image recognition methods based on neural networks. Scientific journal «Computer-integrated technologies: education, science, production». Lutsk. Issue No. 35. С. 161-165 [in Ukrainian].
19. Yarovyi, A.A., Kashubin, S.G., & Kulyk, O.O. (2015). Recognition of mimic microexpressions of the human face. Systems of technical vision and artificial intelligence with image processing and stratification. Vinnytsia: VNTU. С.76-83 [in Ukrainian].
Citations
1. Zhu J., Kaplan R., Johnson J., Fei-Fei L. HiDDeN: Hiding data with deep networks. Advances in Neural Information Processing Systems. 2018. Vol. 31.
2. Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.
3. Zhou C., Paffenroth R. Anomaly detection with robust deep autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017. P. 665–674. URL: http://doi.org/10.1145/3097983.3098052.
4. Hayes J., Danezis G. Generating steganographic images via adversarial training. Advances in Neural Information Processing Systems. 2017. Vol. 30.
5. Montgomery D. C. Design and Analysis of Experiments. John Wiley & Sons, 2017.
6. Gupta S., Joshi R. C., Misra M. A. SeGAN: Segment-based image steganography using generative adversarial network. IET Image Processing. 2019. Vol. 13, No. 10. P. 1706–1713. URL: http://doi.org/10.1049/iet-ipr.2018.6233.
7. Lu X., Li B., Huang J. GAN-based image steganography: review and research trends. IEEE Access. 2019. Vol. 7. P. 179097–179110. URL: http://10.1109/ACCESS.2019.2958574.
8. Zhang R., Wang S., Wang L. Robust deep steganography with pixelwise adversarial training. Neural Computing and Applications. 2021. Vol. 33. P. 2357–2369. URL: http://doi.org/10.1007/s00521-020-05047-2.
9. Nissar A. U., Mir A. H. Classification of steganalysis techniques: A study. Digital Signal Processing. 2010. Vol. 20, No. 6. P. 1758–1770. URL: http://doi.org/10.1016/j.dsp.2010.01.017.
10. Li B., Luo X., Liu T., Huang J. A survey on image steganography and steganalysis. Journal of Information Hiding and Multimedia Signal Processing. 2011. Vol. 2, No. 2. P. 142–172.
11. Ker A. D. Steganalysis of LSB matching in grayscale images. IEEE Signal Processing Letters. 2005. Vol. 12, No. 6. P. 441–444. URL: http://doi.org/10.1109/LSP.2005.847889.
12. Petitcolas F. A. P., Anderson R. J., Kuhn M. G. Information hiding - a survey. Proceedings of the IEEE. 1999. Vol. 87, No. 7. P. 1062–1078. URL: http://doi.org/10.1109/5.771065.
13. Reddy A., Acharya N., Mandal J. K. A new approach to transform domain-based robust steganography using wavelet families. Arabian Journal for Science and Engineering. 2018. Vol. 43. P. 5079–5090. URL: http://doi.org/10.1007/s13369-018-3205-0.
14. Liu Z., Su Z., Hou D., Li H. A robust CNN-based method for image steganography and steganalysis. Multimedia Tools and Applications. 2018. Vol. 77. P. 21769–21785. URL: http://doi.org/10.1007/s11042-018-6089-1.
15. Tang S., Wu X. Adaptive steganography based on deep reinforcement learning. Neurocomputing. 2020. Vol. 370. P. 35–46. URL: http://doi.org/10.1016/j.neucom.2019.08.090.
16. Yu W., Chen S. Improved autoencoder-based image steganography. IEEE Access. 2021. Vol. 9. P. 41395–41406. URL: http://doi.org/10.1109/ACCESS.2021.3064091
17. Duan Y., Yang B., Gao H. Deep hiding in video frames with convolutional neural networks // Information Sciences. 2021. Vol. 551. P. 27–43. URL: http://doi.org/10.1016/j.ins.2020.11.038.
18. Мельник К.В., Мельник В.М., Коптюк Ю.Ю. Дослідження методів розпізнавання зображень на основі нейронних мереж. Науковий журнал "Комп’ютерно-інтегровані технології: освіта, наука, виробництво". Луцьк, 2019. Вип. № 35. С. 161-165.
19. Яровий А.А., Кашубін С.Г., Кулик О.О. Розпізнавання мімічних мікровиразів обличчя людини. Системи технічного зору та штучного інтелекту з обробкою та розшаруванням зображень. Вінниця: ВНТУ, 2015. С.76-83.
Copyright (c) 2025 Dmytro Prokopovych-Tkachenko, Liudmyla Rybalchenko, Yaroslav Derkach
Steganographic Methods in Information Security
About the Authors
Dmytro Prokopovych-Tkachenko, Associate Professor, Candidate of Technical Sciences, Head of the Department of Cyber Security and Information Technologies, University of Customs and Finance, Dnipro, Ukraine, ORCID: https://orcid.org/0000-0002-6590-3898, e-mail: omega2417@gmail.com.
Oksana Markiv, Associate Professor, PhD in Economics (Candidate of Economics Sciences), Associate Professor of the Department of Cyber Security and Information Technologies, University of Customs and Finance, Dnipro, Ukraine, ORCID: https://orcid.org/0000-0003-0413-8296, e-mail: Luda_r@ukr.net
Yaroslav Derkach, PhD student, Kharkiv National University of Radio Electronics, 14 Nauky Avenue, Kharkiv, Ukraine, ORCID: http://orcid.org/0009-0009-7208-370X, e-mail: ciscoflexx@gmail.com
Abstract
Keywords
Full Text:
PDFReferences
1. Zhu J., Kaplan R., Johnson J. & Fei-Fei L. (2018). HiDDeN: Hiding data with deep networks. Advances in Neural Information Processing Systems. Vol. 31.
2. Goodfellow I., Bengio Y. & Courville A. (2016). Deep Learning. MIT Press.
3. 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. P. 665–674. http://doi.org/10.1145/3097983.3098052.
4. Hayes J. & Danezis G. (2017). Generating steganographic images via adversarial training. Advances in Neural Information Processing Systems. Vol. 30.
5. Montgomery D. C. (2017). Design and Analysis of Experiments. John Wiley & Sons.
6. Gupta S., Joshi R. C. & Misra M. A. (2019). SeGAN: Segment-based image steganography using generative adversarial network. IET Image Processing. Vol. 13, No. 10. P. 1706–1713. http://doi.org/10.1049/iet-ipr.2018.6233.
7. Lu X., Li B. & Huang J. (2019). GAN-based image steganography: review and research trends. IEEE Access. Vol. 7. P. 179097–179110. http://10.1109/ACCESS.2019.2958574.
8. Zhang R., Wang S. & Wang L. (2021). Robust deep steganography with pixelwise adversarial training. Neural Computing and Applications. Vol. 33. P. 2357–2369. http://doi.org/10.1007/s00521-020-05047-2
9. Nissar A. U. & Mir A. H. (2010). Classification of steganalysis techniques: A study. Digital Signal Processing. Vol. 20, No. 6. P. 1758–1770. http://doi.org/10.1016/j.dsp.2010.01.017.
10. Li B., Luo X., Liu T. & Huang J. (2011). A survey on image steganography and steganalysis. Journal of Information Hiding and Multimedia Signal Processing. Vol. 2, No. 2. P. 142–172.
11. Ker A. D. (2005). Steganalysis of LSB matching in grayscale images. IEEE Signal Processing Letters. Vol. 12, No. 6. P. 441–444. http://doi.org/10.1109/LSP.2005.847889.
12. Petitcolas F. A. P., Anderson R. J. & Kuhn M. G. (1999). Information hiding - a survey. Proceedings of the IEEE. Vol. 87, No. 7. P. 1062–1078. http://doi.org/10.1109/5.771065.
13. 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. Vol. 43. P. 5079–5090. http://doi.org/10.1007/s13369-018-3205-0.
14. Liu Z., Su Z. & Hou D., Li H. (2018). A robust CNN-based method for image steganography and steganalysis. Multimedia Tools and Applications. Vol. 77. P. 21769–21785. http://doi.org/10.1007/s11042-018-6089-1.
15. Tang S. & Wu X. (2020). Adaptive steganography based on deep reinforcement learning. Neurocomputing. Vol. 370. P. 35–46. http://doi.org/10.1016/j.neucom.2019.08.090.
16. Yu W. & Chen S. (2021). Improved autoencoder-based image steganography. IEEE Access. Vol. 9. P. 41395–41406. http://doi.org/10.1109/ACCESS.2021.3064091
17. Duan Y., Yang B., & Gao H. (2021). Deep hiding in video frames with convolutional neural networks // Information Sciences. Vol. 551. P. 27–43. http://doi.org/10.1016/j.ins.2020.11.038.
18. Melnyk, K.V., Melnyk, V.M., & Koptyuk, Y.Y. (2019). Research of image recognition methods based on neural networks. Scientific journal «Computer-integrated technologies: education, science, production». Lutsk. Issue No. 35. С. 161-165 [in Ukrainian].
19. Yarovyi, A.A., Kashubin, S.G., & Kulyk, O.O. (2015). Recognition of mimic microexpressions of the human face. Systems of technical vision and artificial intelligence with image processing and stratification. Vinnytsia: VNTU. С.76-83 [in Ukrainian].
Citations
1. Zhu J., Kaplan R., Johnson J., Fei-Fei L. HiDDeN: Hiding data with deep networks. Advances in Neural Information Processing Systems. 2018. Vol. 31.
2. Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.
3. Zhou C., Paffenroth R. Anomaly detection with robust deep autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017. P. 665–674. URL: http://doi.org/10.1145/3097983.3098052.
4. Hayes J., Danezis G. Generating steganographic images via adversarial training. Advances in Neural Information Processing Systems. 2017. Vol. 30.
5. Montgomery D. C. Design and Analysis of Experiments. John Wiley & Sons, 2017.
6. Gupta S., Joshi R. C., Misra M. A. SeGAN: Segment-based image steganography using generative adversarial network. IET Image Processing. 2019. Vol. 13, No. 10. P. 1706–1713. URL: http://doi.org/10.1049/iet-ipr.2018.6233.
7. Lu X., Li B., Huang J. GAN-based image steganography: review and research trends. IEEE Access. 2019. Vol. 7. P. 179097–179110. URL: http://10.1109/ACCESS.2019.2958574.
8. Zhang R., Wang S., Wang L. Robust deep steganography with pixelwise adversarial training. Neural Computing and Applications. 2021. Vol. 33. P. 2357–2369. URL: http://doi.org/10.1007/s00521-020-05047-2.
9. Nissar A. U., Mir A. H. Classification of steganalysis techniques: A study. Digital Signal Processing. 2010. Vol. 20, No. 6. P. 1758–1770. URL: http://doi.org/10.1016/j.dsp.2010.01.017.
10. Li B., Luo X., Liu T., Huang J. A survey on image steganography and steganalysis. Journal of Information Hiding and Multimedia Signal Processing. 2011. Vol. 2, No. 2. P. 142–172.
11. Ker A. D. Steganalysis of LSB matching in grayscale images. IEEE Signal Processing Letters. 2005. Vol. 12, No. 6. P. 441–444. URL: http://doi.org/10.1109/LSP.2005.847889.
12. Petitcolas F. A. P., Anderson R. J., Kuhn M. G. Information hiding - a survey. Proceedings of the IEEE. 1999. Vol. 87, No. 7. P. 1062–1078. URL: http://doi.org/10.1109/5.771065.
13. Reddy A., Acharya N., Mandal J. K. A new approach to transform domain-based robust steganography using wavelet families. Arabian Journal for Science and Engineering. 2018. Vol. 43. P. 5079–5090. URL: http://doi.org/10.1007/s13369-018-3205-0.
14. Liu Z., Su Z., Hou D., Li H. A robust CNN-based method for image steganography and steganalysis. Multimedia Tools and Applications. 2018. Vol. 77. P. 21769–21785. URL: http://doi.org/10.1007/s11042-018-6089-1.
15. Tang S., Wu X. Adaptive steganography based on deep reinforcement learning. Neurocomputing. 2020. Vol. 370. P. 35–46. URL: http://doi.org/10.1016/j.neucom.2019.08.090.
16. Yu W., Chen S. Improved autoencoder-based image steganography. IEEE Access. 2021. Vol. 9. P. 41395–41406. URL: http://doi.org/10.1109/ACCESS.2021.3064091
17. Duan Y., Yang B., Gao H. Deep hiding in video frames with convolutional neural networks // Information Sciences. 2021. Vol. 551. P. 27–43. URL: http://doi.org/10.1016/j.ins.2020.11.038.
18. Мельник К.В., Мельник В.М., Коптюк Ю.Ю. Дослідження методів розпізнавання зображень на основі нейронних мереж. Науковий журнал "Комп’ютерно-інтегровані технології: освіта, наука, виробництво". Луцьк, 2019. Вип. № 35. С. 161-165.
19. Яровий А.А., Кашубін С.Г., Кулик О.О. Розпізнавання мімічних мікровиразів обличчя людини. Системи технічного зору та штучного інтелекту з обробкою та розшаруванням зображень. Вінниця: ВНТУ, 2015. С.76-83.