DETECTION OF STEGANOGRAPHY IN IMAGES USING LIGHTWEIGHT DEEP LEARNING MODELS
DOI:
https://doi.org/10.28925/2663-4023.2026.32.1086Keywords:
stegoanalysis, deep learning, EfficientNet, MobileNet, HPF, convolutional neural networks, residual noiseAbstract
This paper presents a comprehensive experimental study on the applicability of lightweight convolutional neural networks (CNNs) for the task of digital image steganalysis under resource-constrained conditions. The main objective of the research is to evaluate whether compact architectures such as MobileNetV2 and EfficientNetV2S can achieve high detection accuracy when combined with appropriate high-frequency preprocessing, while significantly reducing computational and memory requirements compared to heavy specialized steganalytic networks.
The study demonstrates that high-pass filtering (HPF) is a critical prerequisite for effective steganography detection. Without explicit suppression of image content, lightweight CNNs fail to distinguish weak stego-noise from natural image structures. Experimental results show that an insufficient number of HPF layers or filters leads to rapid overfitting and unstable classification performance. In contrast, the use of a sufficiently expressive and structured HPF preprocessing block enables stable convergence and high generalization ability.
Special attention is paid to the influence of fixed versus trainable HPF filters. It is shown that allowing HPF kernels to adapt during training provides an additional performance gain by adjusting to the statistical characteristics of stego-noise. This hybrid approach effectively combines prior knowledge from classical steganalysis (SRM-based filters) with the adaptive capabilities of deep learning.
The proposed detection framework was evaluated using images with data embedded by the least significant bit (LSB) method under various payload conditions. Both MobileNetV2 and EfficientNetV2S demonstrated high detection accuracy and near-optimal ROC characteristics while maintaining low computational complexity. These results confirm that lightweight CNN architectures, when properly augmented with high-frequency preprocessing, represent a viable solution for practical steganalysis, including deployment on embedded or mobile platforms.
However, the current evaluation is limited to LSB-based embedding. Future work will focus on extending the proposed approach to more sophisticated adaptive steganographic algorithms and on improving robustness across different image domains.
Downloads
References
. Fridrich, Jessica. (2010). Steganography in Digital Media: Principles, Algorithms, and Applications. Steganography in Digital Media. 10.1017/CBO9781139192903.
. Fridrich and J. Kodovsky, "Rich Models for Steganalysis of Digital Images," in IEEE Transactions on Information Forensics and Security, vol. 7, no. 3, pp. 868-882, June 2012, doi: 10.1109/TIFS.2012.2190402.
. Ma, Yuanyuan & Wang, Jian & Zhang, Xinyu & Wang, Guifang & Xin, Xianwei & Zhang, Qianqian. (2025). LGS‐Net: A lightweight convolutional neural network based on global feature capture for spatial image steganalysis. IET Image Processing. 19. 10.1049/ipr2.70005.
. Karamanji, Awab & Ahmed, Asia & Fadhil, Ali. (2024). Comparative Deep Learning Models in Applications of Steganography Detection. Journal of Image and Graphics. 12. 312-319. 10.18178/joig.12.3.312-319.
. Zhang, R., Zhu, F., Liu, J., & Liu, G. (2018). Efficient feature learning and multi-size image steganalysis based on CNN. ArXiv, abs/1807.11428.
. Agarwal, S., & Jung, K.-H. (2022). Identification of Content-Adaptive Image Steganography Using Convolutional Neural Network Guided by High-Pass Kernel. Applied Sciences, 12(22), 11869. https://doi.org/10.3390/app122211869
. Deng, XQ., Chen, BL., Luo, WQ. et al. Universal Image Steganalysis Based on Convolutional Neural Network with Global Covariance Pooling. J. Comput. Sci. Technol. 37, 1134–1145 (2022). https://doi.org/10.1007/s11390-021-0572-0
. Yatsura, Pavlo & Progonov, Dmytro. (2025). A Review of modern methods for steganalysis and localization of embedded data in digital images. Theoretical and Applied Cybersecurity. 7. 10.20535/tacs.2664-29132025.1.328265.
. L. I. Hao, Z. Yi, W. Jinwei, Z. Weiming, and L. U. O. Xiangyang, “Lightweight Steganography Detection Method Based on Multiple Residual Structures and Transformer,” dzxbyw, vol. 33, no. 4, pp. 965–978, Jul. 2024, doi: 10.23919/cje.2022.00.452.
. W. Mazurczyk and L. Caviglione, “Steganography in Modern Smartphones and Mitigation Techniques,” Aug. 27, 2014, arXiv: arXiv:1410.6796. Accessed: Nov. 08, 2024. [Online]. Available: http://arxiv.org/abs/1410.6796
. Chen, Niusen & Chen, Bo. (2022). Defending against OS-Level Malware in Mobile Devices via Real-Time Malware Detection and Storage Restoration. Journal of Cybersecurity and Privacy. 2. 10.3390/jcp2020017.
. M. Boroumand, M. Chen, and J. Fridrich, “Deep Residual Network for Steganalysis of Digital Images,” IEEE Trans.Inform.Forensic Secur., vol. 14, no. 5, pp. 1181–1193, May 2019, doi: 10.1109/TIFS.2018.2871749.
. J. Ye, J. Ni and Y. Yi, "Deep Learning Hierarchical Representations for Image Steganalysis," in IEEE Transactions on Information Forensics and Security, vol. 12, no. 11, pp. 2545-2557, Nov. 2017, doi: 10.1109/TIFS.2017.2710946.
. Zhang, R., Zhu, F., Liu, J., & Liu, G. (2018). Efficient feature learning and multi-size image steganalysis based on CNN. ArXiv, abs/1807.11428.
. Hu, Fengsong & Xu, Rong & Cheng, Zhekun. (2021). A fast and effective image steganalysis model based on convolutional neural network. Journal of Physics: Conference Series. 1861. 012074. 10.1088/1742-6596/1861/1/012074.
. Agarwal, S., Kim, H., & Jung, K.-H. (2023). High-Pass-Kernel-Driven Content-Adaptive Image Steganalysis Using Deep Learning. Mathematics, 11(20), 4322. https://doi.org/10.3390/math11204322
. Yinlong Qian, Jing Dong, Wei Wang, and Tieniu Tan "Deep learning for steganalysis via convolutional neural networks", Proc. SPIE 9409, Media Watermarking, Security, and Forensics 2015, 94090J (4 March 2015); https://doi.org/10.1117/12.2083479
. Holub, Vojtech & Fridrich, Jessica. (2012). Designing Steganographic Distortion Using Directional Filters. WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security. 10.1109/WIFS.2012.6412655.
. Hussain, Israr & Zeng, Jishen & Tan, Shunquan. (2020). A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis. KSII Transactions on Internet and Information Systems. 14. 1228-1248. 10.3837/tiis.2020.03.017.
. Wu, Lan & Han, Xiaolei & Wen, Chenglin & Li, Binquan. (2020). A Steganalysis framework based on CNN using the filter subset selection method. Multimedia Tools and Applications. 79. 10.1007/s11042-020-08831-8.
. Krizhevsky, Alex. (2012). Learning Multiple Layers of Features from Tiny Images. University of Toronto.
. DiSalvo, N. (2025). Steganographic Embeddings as an Effective Data Augmentation. ArXiv, abs/2502.15245.
. Stefanek G., Gulbransen L., Spink G., Morawski J., Filla D., Rabello De Castro R. A comparison of ai models to detect hidden messages in images. (2024). Issues In Information Systems. 119-132. https://doi.org/10.48009/3_iis_2024_110
. K, V., Annem, P., Devarakonda, M., Jyothi, A., & Rayudu, N. (2025). Image Steganography with CNN Based Encoder - Decoder. International Journal for Modern Trends in Science and Technology, 11(04), 60–64. https://doi.org/10.5281/zenodo.15108976
. Fridrich, Jessica & Goljan, Miroslav & Du, Rui. (2001). Detecting LSB steganography in color, and gray-scale images. Multimedia, IEEE. 8. 22 - 28. 10.1109/93.959097.
. Meike Helena Kombrink, Zeno Jean Marius Hubert Geradts, and Marcel Worring. 2024. Image Steganography Approaches and Their Detection Strategies: A Survey. ACM Comput. Surv. 57, 2, Article 33 (February 2025), 40 pages. https://doi.org/10.1145/3694965
. Bauravindah, Achmad & Fudholi, Dhomas. (2024). Lightweight Models for Real-Time Steganalysis: A Comparison of MobileNet, ShuffleNet, and EfficientNet. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 8. 737-747. 10.29207/resti.v8i6.6091.
. Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., & Chen, L. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4510-4520.
. Zhou, Aihua & Ma, Yujun & Ji, Wanting & Zong, Ming & Yang, Pei & Wu, Min & Liu, Mingzhe. (2022). Multi-head attention-based two-stream EfficientNet for action recognition. Multimedia Systems. 29. 1-12. 10.1007/s00530-022-00961-3.
. Farooq N., Mir R. Image Steganalysis using Deep Convolution Neural Networks: A Literature Survey // International Journal of Sensors, Wireless Communications and Control. - 2024. - Vol. 14. - N. 4. - P. 247-264. doi: 10.2174/0122103279296370240529075507
. Chaumont, Marc. (2020). Deep learning in steganography and steganalysis. 10.1016/B978-0-12-819438-6.00022-0.
. S. Wu, S. -h. Zhong and Y. Liu, "A Novel Convolutional Neural Network for Image Steganalysis With Shared Normalization," in IEEE Transactions on Multimedia, vol. 22, no. 1, pp. 256-270, Jan. 2020, doi: 10.1109/TMM.2019.2920605.
. Dwaik, A., & Belkhouche, Y. (2024). Enhancing the performance of convolutional neural network image-based steganalysis in spatial domain using Spatial Rich Model and 2D Gabor filters. Journal of Information Security and Applications, 85, 103864. https://doi.org/10.1016/j.jisa.2024.103864
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Наталія Лащевська, Юрій Мішкур
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
