An Artificial Intelligence-Based Framework for Detecting Hidden Information in Stego Images for Secure Digital Communication
Downloads
Cybersecurity and digital forensics face numerous obstacles due to steganography, the practice of concealing a message within a digital image file. However, because of the minimal visible changes in images with the current steganographic techniques, it is difficult to detect the hidden data effectively. The creation of an efficient DL-based steganalysis framework that can enhance the identification of hidden information in pictures in the spatial domain is the primary objective of this study. An enhanced Convolutional Neural Network (CNN) model is proposed and tested on the basis of the BOSS Base 1.01 dataset. The steganographic algorithms used in the study (S-UNIWARD and WOW) were developed to produce stego images having a payload of 0.4 bpp. The proposed CNN model achieved better feature extraction and classification accuracy than the alternatives when asked to distinguish between cover pictures and stego images. The results of the experiments demonstrated that the model was 87.6% accurate for WOW and 84.5% accurate for S-UNIWARD. It was discovered that numerous existing methods, such as ResNet, Alex Net, and CVTStego-Net, performed lower than the benchmark. There was little overfitting and consistent convergence in the validation and training curves. As a whole, the suggested architecture helps with safe digital forensics and cybersecurity applications while also providing a solid, dependable, and efficient solution for image steganalysis.
B. Singh, M. A. Augie, H. Singh, and T. Banerjee, “Strengthening Modern IAM Authentication with Quantum Cryptography and Anti-Phishing Techniques,” Sarcouncil J. Eng. Comput. Sci., vol. 04, no. 10, pp. 17–31, October, 2025,
doi: 10.5281/zenodo.17260292.
A. Nath, S. Das, R. Sharma, and S. Mandal, “Digital Steganography : A Comprehensive Study on Various Methods for Hiding Secret Data in a Cover file,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 10, no. 3, pp. 291–300, May 2024,
doi: 10.32628/CSEIT24103107.
L. Zeng, N. Yang, X. Li, A. Chen, H. Jing, and J. Zhang, “Advanced Image Steganography Using a U-Net-Based Architecture with Multi-Scale Fusion and Perceptual Loss,” Electronics, vol. 12, no. 18, p. 3808, Sep. 2023, doi: 10.3390/electronics12183808.
K. Chinniyan, T. Vani Samiyappan, A. Gopu, and N. Ramasamy, “Image Steganography Using Deep Neural Networks,” Intell. Autom. Soft Comput., vol. 34, no. 3, pp. 1877–1891, 2022, doi: 10.32604/iasc.2022.027274.
C. Han and T. Xue, “Adaptive network steganography using deep learning and multimedia video analysis for enhanced security and fidelity,” PLoS One, vol. 20, no. 6, p. e0318795, Jun. 2025,
doi: 10.1371/journal.pone.0318795.
A. Cheddad, J. Condell, K. Curran, and P. Mc Kevitt, “Digital image steganography: Survey and analysis of current methods,” Signal Processing, vol. 90, no. 3, pp. 727–752, Mar. 2010,
doi: 10.1016/j.sigpro.2009.08.010.
B. Jeganathan, “Exploring the Power of Generative Adversarial Networks (GANs) for Image Generation: A Case Study on the MNIST Dataset,” Int. J. Adv. Eng. Manag., vol. 7, no. 1, pp. 21–46, Jan. 2025,
doi: 10.35629/5252-07012146.
P. M. Kumar and J. A. Renjith, “An image steganographic algorithm on smart mechanism of embedding secret data in images,” Int. J. Electron. Secur. Digit. Forensics, vol. 8, no. 1, p. 35, 2016, doi: 10.1504/IJESDF.2016.073732.
S. K. Davuluri, V. Challagulla, V. Mudapaka, and U. Konka, “Telcoformrix: An AI-Augmented Framework for Declarative and Scalable Provisioning of Real-Time Communication Infrastructure (Work in Progress),” in 2025 IEEE International Conference and Expo on Real Time Communications at IIT (RTC), Chicago, IL, USA: IEEE, 2025, pp. 1–4, October.
doi: 10.1109/RTC66985.2025.11211725.
M. Płachta, M. Krzemień, K. Szczypiorski, and A. Janicki, “Detection of Image Steganography Using Deep Learning and Ensemble Classifiers,” Electron., 2022, doi: 10.3390/electronics11101565.
M. V. Kumar and P. Pandiaraj, “Content dependent data hiding on GSM full rate encoded image,” in 2011 3rd International Conference on Electronics Computer Technology, IEEE, Apr. 2011, pp. 406–409.
doi: 10.1109/ICECTECH.2011.5941781.
L. Caviglione et al., “Tight Arms Race: Overview of Current Malware Threats and Trends in Their Detection,” IEEE Access, vol. 9, pp. 5371–5396, 2021, doi: 10.1109/ACCESS.2020.3048319.
O. Kuznetsov, E. Frontoni, K. Chernov, K. Kuznetsova, R. Shevchuk, and M. Karpinski, “Enhancing Steganography Detection with AI: Fine-Tuning a Deep Residual Network for Spread Spectrum Image Steganography,” Sensors, vol. 24, no. 23, p. 7815, Dec. 2024, doi: 10.3390/s24237815.
S. Geetha, V. Kabilan, S. P. Chockalingam, and N. Kamaraj, “Varying radix numeral system based adaptive image steganography,” Inf. Process. Lett., vol. 111, no. 16, pp. 792–797, Aug. 2011,
doi: 10.1016/j.ipl.2011.05.013.
S. Agarwal and K.-H. Jung, “Digital image steganalysis using entropy driven deep neural network,” J. Inf. Secur. Appl., vol. 84, p. 103799, Aug. 2024, doi: 10.1016/j.jisa.2024.103799.
A. Banerjee, S. Ganguly, I. Mukherjee, and N. Ganguly, “Towards secure digital media: A drift-aware MLOps framework for adaptive stego content sterilization,” Futur. Gener. Comput. Syst., vol. 183, p. 108546, Oct. 2026,
doi: 10.1016/j.future.2026.108546.
K. Thapliyal, S. Mukherjee, R. Gateru, and M. Manchanda, “Decoding Hidden Communication: Image Steganography and Steganalysis via Feature Extraction,” in 2025 IEEE Pune Section International Conference (PuneCon), IEEE, Dec. 2025, pp. 1–5. doi: 10.1109/PuneCon67554.2025.11378501.
S. Dhawan et al., “Secure and resilient improved image steganography using hybrid fuzzy neural network with fuzzy logic,” J. Saf. Sci. Resil., vol. 5, no. 1, pp. 91–101, Mar. 2024,
doi: 10.1016/j.jnlssr.2023.12.003.
A. Melman and O. Evsutin, “Comparative study of metaheuristic optimization algorithms for image steganography based on discrete Fourier transform domain,” Appl. Soft Comput., vol. 132, p. 109847, Jan. 2023, doi: 10.1016/j.asoc.2022.109847.
J. Liu, G. Jiao, and X. Sun, “Feature Passing Learning for Image Steganalysis,” IEEE Signal Process. Lett., vol. 29, pp. 2233–2237, 2022,
doi: 10.1109/LSP.2022.3217444.
O. A. Alrusaini, “Deep learning for steganalysis: evaluating model robustness against image transformations,” Front. Artif. Intell., vol. 8, Mar. 2025, doi: 10.3389/frai.2025.1532895.
M. A. Bravo-Ortiz et al., “CVTStego-Net: A convolutional vision transformer architecture for spatial image steganalysis,” J. Inf. Secur. Appl., vol. 81, p. 103695, Mar. 2024,
doi: 10.1016/j.jisa.2023.103695.
Z. Wang, M. Chen, Y. Yang, M. Lei, and Z. Dong, “Joint multi-domain feature learning for image steganalysis based on CNN,” EURASIP J. Image Video Process., vol. 2020, no. 1, p. 28, Dec. 2020,
doi: 10.1186/s13640-020-00513-7.
A. Q. Karamanji, A. S. Ahmed, and A. F. Fadhil, “Comparative Deep Learning Models in Applications of Steganography Detection,” J. Image Graph., vol. 12, no. 3, pp. 312–319, 2024,
doi: 10.18178/joig.12.3.312-319.
