A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness

References

[1] Abdulla, A. A. (2015). Steganography and steganalysis: A review. International Journal of Computer Applications, 119(3), 1-6.

[2] Agarwal, R., & Jung, C. R. (2024). Entropy-driven CNN with SRM filters for spatial image steganalysis. IEEE Transactions on Information Forensics and Security, 19, 1123-1135.

[3] Akrout, M., Feriani, A., Bellili, F., Mezghani, I., & Hossain, E. (2023). Machine learning for cybersecurity in smart grids: A comprehensive review. IEEE Communications Surveys & Tutorials, 25(1), 548-589.

[4] Al-Obaidi, A. T. S., Jalab, H. A., & Kahtan, H. (2024). A reinforcement learning and generative adversarial network framework for image steganalysis. Multimedia Tools and Applications, 83(7), 20145-20172.

[5] Alrusaini, A. M. (2025). Systematic evaluation of deep learning steganalysis architectures under real-world image transformations. Journal of King Saud University - Computer and Information Sciences, 37(2), 103-118.

[6] Bamanga, M., & Babando, A. S. (2024). Content-adaptive steganography and deep learning-based steganalysis: A survey. International Journal of Advanced Computer Science and Applications, 15(4), 78-92.

[7] Bas, P., Filler, T., & Pevny, T. (2011). Break our steganographic system: The ins and outs of organizing BOSS. In International Workshop on Information Hiding (pp. 59-70). Springer.

[8] Bell, J. (2022). Machine learning: A comprehensive foundation. Wiley.

[9] Bohang, M., Li, S., & Wang, X. (2025). Active learning with deep reinforcement learning for efficient image steganalysis. Pattern Recognition, 158, 110-124.

[10] Borse, Y. J., Anand, D. V., & Patel, N. S. (2013). A review on steganography: Classification, methods, and applications. International Journal of Engineering Research & Technology, 2(7), 1-6.

[11] Boroumand, M., Chen, M., & Fridrich, J. (2019). Deep residual network for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 14(5), 1181-1193.

[12] Bravo-Ortiz, M., Xiao, B., & Yedroudj, Y. (2024). CVTStego-Net: Convolutional vision transformer for spatial image steganalysis. IEEE Signal Processing Letters, 31, 1456-1460.

[13] Cheddad, A. (2009). Digital image steganography: Survey and analysis of current methods. Glasgow Caledonian University.

[14] Cheddad, A., Condell, J., Curran, K., & McKevitt, P. (2010). Digital image steganography: Survey and analysis of current methods. Signal Processing, 90(3), 727-752.

[15] De La Croix, J. P., Putra, R. V. W., & Ahmad, M. (2024a). Payload localization in spatial image steganalysis using CNN with genetic algorithm pooling. Journal of Information Security and Applications, 82, 103-117.

[16] De La Croix, J. P., Putra, R. V. W., & Ahmad, M. (2024b). Advances in locative steganalysis: Techniques and challenges. Digital Investigation, 48, 301-315.

[17] Doshi, R., Jain, N., & Gupta, S. (2012). Steganography and its applications in security. International Journal of Computer Science and Management Research, 1(2), 1-6.

[18] Dwaik, M., & Belkhouche, F. (2024). CNN with SRM and Gabor filters for robust image steganalysis across heterogeneous datasets. Computers & Security, 139, 103-118.

[19] Eid, H., Samy, E., El-Soudani, M., & El-Kharashi, M. W. (2022). Image steganalysis using deep learning: A comprehensive survey. Multimedia Tools and Applications, 81(1), 1-45.

[20] Farid, H. (2003). Detecting steganographic messages in digital images. Technical Report, Dartmouth College, Hanover, NH.

[21] Fridrich, J., & Kodovsky, J. (2012). Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 7(3), 868-882.

[22] Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7132-7141).

[23] Hu, Y., & Wang, C. (2023). TStegNet: Two-stream CNN for adversarial steganography detection. Information Sciences, 639, 119-134.

[24] Hu, Y., & Wang, C. (2025). Directional adversarial noise for robust steganalysis defense. Expert Systems with Applications, 238, 121-135.

[25] Huang, Y., Zhang, Y., & Li, M. (2024). FACSNet: Forensics aided content selection network for heterogeneous image steganalysis. IEEE Transactions on Circuits and Systems for Video Technology, 34(5), 3456-3469.

[26] Jawad, A., Mohasefi, J. B., & Abdelghany, M. A. (2025). EfficientNet-based adversarial training for robust image steganalysis. Neural Computing and Applications, 37(3), 1201-1215.

[27] Kadhim, I. J., Premaratne, P., Vial, P. J., & Halloran, B. (2019). A review on steganalysis: A comprehensive study of feature extraction in image steganalysis. Journal of Network and Computer Applications, 128, 1-24.

[28] Kahn, D. (1996). The history of steganography. In Proceedings of the First International Workshop on Information Hiding (pp. 1-5). Springer.

[29] Karampidis, K., Kavallieratou, E., & Papadourakis, G. (2018). Image steganalysis: A review of current methods and challenges. Journal of Information Security and Applications, 40, 1-15.

[30] Ke, Y., & Sheng, B. (2019). Co-occurrence features with RealAdaBoost for spatial domain steganalysis. In IEEE International Conference on Image Processing (ICIP) (pp. 4230-4234).

[31] Kheddar, Y., Mokraoui, A., & Ni, Z. (2024). Challenges in modern steganalysis: From dimensionality curse to adversarial fragility. IEEE Access, 12, 34567-34589.

[32] Kenney, J., Rahman, S., & Bhadra, J. (2021). Deep learning approaches for image steganalysis: A comparative study. Journal of Cybersecurity, 7(2), 89-104.

[33] Krenn, R. (2004). Steganography and steganalysis. Technical Report, Vienna University of Technology.

[34] Li, S., & Dong, F. (2024). CNN with channel attention for image steganalysis in communication security. Computer Networks, 240, 110-124.

[35] Li, W., & Liu, J. (2015). Steganalysis of multi-carrier spread-spectrum steganography. IEEE Transactions on Information Forensics and Security, 10(9), 1855-1868.

[36] Li, Z., Wang, Y., Song, X., & Wang, H. (2024). FPFNet: Feature pyramid fusion network for image steganalysis. Signal Processing: Image Communication, 127, 117-129.

[37] Lie, W. N., & Lin, G. S. (2005). A feature-based classification technique for blind image steganalysis. IEEE Transactions on Multimedia, 7(6), 979-992.

[38] Liu, Y., Chen, Z., & Zhao, X. (2023). TCSI-ECA transfer learning for low-rate steganalysis detection. IEEE Transactions on Information Forensics and Security, 18, 2345-2358.

[39] Lu, P., Li, X., & Chen, H. (2019). Truncated linear unit (TLU) preprocessing for CNN-based spatial and JPEG steganalysis. In Proceedings of the ACM Workshop on Information Hiding and Multimedia Security (pp. 67-72).

[40] Lu, S., Wang, R., & Zhang, X. (2020). Deep learning for image steganalysis: A survey. IEEE Access, 8, 203207-203224.

[41] Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations (ICLR).

[42] Mandal, S., Mandal, S., & Das, S. (2022). Advances in digital steganography: A comprehensive review. Computer Science Review, 46, 100-118.

[43] Mo, Y., Chen, H., & Wang, L. (2023). Wavelet decomposition with CNN clustering for content-aware steganalysis. Pattern Recognition Letters, 168, 45-52.

[44] Mohamed, L. A., Rabie, T., & Kamel, I. (2020). A comprehensive survey of color image steganalysis in the transform domain. Multimedia Tools and Applications, 79(1), 1-32.

[45] Peng, P., Yu, J., Fu, Y., Zhang, J., & Duan, X. (2024). RS-GAN: Robust steganalysis via generative adversarial network disentanglement. IEEE Transactions on Information Forensics and Security, 19, 567-580.

[46] Qiao, T., Li, L., & Dong, J. (2022). Adversarial steganography and steganalysis: A survey. IEEE Transactions on Circuits and Systems for Video Technology, 32(4), 2021-2036.

[47] Qin, C., Ji, P., Zhang, X., Dong, J., & Wang, J. (2020). Fractal image coding-based steganography with adversarial attack resistance. IEEE Access, 8, 98765-98778.

[48] Rafat, K. A., & Sajjad, M. (2024). Digital steganography: Evolution, techniques, and modern applications. Egyptian Informatics Journal, 25(1), 1-18.

[49] Rahman, M. S., Rahman, M. A., & Hossain, M. S. (2023). Image steganography and steganalysis: A comprehensive survey. ACM Computing Surveys, 55(8), 1-38.

[50] Sellars, D. (2007). An introduction to steganography and steganalysis. Master's Thesis, University of Pretoria.

[51] Selvaraj, A. I., Sundararajan, R., & Priya, S. L. (2021). Machine learning techniques for steganalysis: A review. Artificial Intelligence Review, 54(6), 4103-4132.

[52] Shankar, K., & Azhakath, N. (2019). Statistical steganalysis of JPEG images using SVM-PSO hybrid classifier. Security and Communication Networks, 2019, 1-14.

[53] Shih, F. Y. (2017). Digital Watermarking and Steganography: Fundamentals and Techniques. CRC Press.

[54] Tripathi, S., Singh, R., & Singh, A. (2016). A review on steganography techniques: Past, present and future. International Journal of Computer Applications, 135(1), 1-10.

[55] Wu, S., Zhong, S., & Liu, Y. (2018). Deep joint discrimination network for steganalysis. IEEE Transactions on Information Forensics and Security, 14(5), 1181-1193.

[56] Yahya, A. (2019). Feature extraction techniques in steganalysis: A comparative study. Journal of Applied Sciences, 19(3), 78-89.

[57] Yang, F., Chen, X., & Wang, Z. (2024). Hybrid CNN with attention fusion for spatial domain steganalysis. Neurocomputing, 568, 127-138.

[58] Yu, X., Tan, T., & Schaefer, G. (2024). Dominant feature selection with compensation for efficient image steganalysis. IEEE Transactions on Image Processing, 33, 2345-2358.

[59] Zhengliang, W., Chen, Y., & Li, H. (2025). SG-ResNet: Dual-stream Gabor residual network for joint steganalysis and payload reconstruction. IEEE Signal Processing Letters, 32, 345-349.

@article{1718767,
      author = {Shehu Asmau, Kirubakaran Prema, Muhammad L. Bilkisu},
      title = {A Comprehensive Survey of Deep Learning-Based Image Steganalysis: From Statistical Methods to Adversarial Robustness},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {12},
      pages = {1372-1383},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1718767.pdf},
      abstract = {This survey presents an overview of the development of image steganalysis from basic statistical models to the latest deep learning architectures. A total of 24 significant studies were analyzed, which are grouped into six important dimensions: embedding domain coverage, dataset diversity, low-payload sensitivity, adversarial robustness, pixel-level defense evaluation, computational efficiency. It also shows that the literature is fragmented, with no existing model that effectively covers the cases of heterogeneous dual-domain detection, realistic adversarial robustness on pixel level, and lightweight deployment. Three main gaps were identified: cover-source mismatch in the case of homogeneous training data, single domain architectural limitations, feature space adversarial evaluation that does not represent actual threat models; a unified taxonomy for future research is proposed. This survey provides a well-founded base for quantifying dataset heterogeneity from an information theoretic perspective, providing a principled ground for assessing generalisability in steganalysis systems.},
      keywords = {Adversarial Robustness, Dual-Domain Detection, Cover-Source Mismatch, Steganalysis.},
      month = {June},
      doi = {https://doi.org/10.64388/IREV9I12-1718767}
  }