A Secure Autoencoder–Based Steganography Method Using Garsia–Wachs Huffman Coding and Uniform Gradient Discriminative Learning
Received: 13 April 2026 | Revised: 29 April 2026 | Accepted: 9 May 2026 | Online: 6 June 2026
Corresponding author: R. Padma
Abstract
With increasing concerns about security threats during the transmission of valuable data, the role played by steganography is of prime importance. Although the adoption of deep learning for optimization is increasing, it has been observed that it may also lead to degraded performance and reduced data quality. Hence, this manuscript presents an innovative yet simplified computational model for steganography, termed the Garsia–Wachs Huffman Coding and Uniform Gradient Discriminative Autoencoder (GWHC-UGDA). Unlike frequently adopted deep learning models, the proposed model uses an autoencoder to improve image quality and to increase extraction accuracy. The system uses Mutual Normalized Histogram analysis as well as Garsia–Wachs Optimal Huffman Coding for separately processing cover and secret information. The system also contributes to enhancing robustness and minimizing extraction error using a Disentangled and Gradient-Discriminative Log-Likelihood Autoencoder (DGDLLA). Implemented in Python using a standard dataset, the model achieves 21–31% higher extraction accuracy with up to 60% reduction in extraction error in contrast to baseline models.
Keywords:
steganography, deep learning, autoencoder, extraction, Huffman coding, histogram analysisReferences
V. K. Sharma, R. N. Mir, and R. K. Rout, "Towards secured image steganography based on content-adaptive adversarial perturbation," Computers and Electrical Engineering, vol. 105, Jan. 2023, Art. no. 108484.
H. Zhang, F. Liu, Z. Song, X. Zhang, and Y. Zhao, "AG-Net: An Advanced General CNN Model for Steganalysis," IEEE Access, vol. 10, pp. 44116–44122, 2022.
A. A. Mawgoud, M. H. N. Taha, A. Abu-Talleb, and A. Kotb, "A deep learning based steganography integration framework for ad-hoc cloud computing data security augmentation using the V-BOINC system," Journal of Cloud Computing, vol. 11, no. 1, Dec. 2022, Art. no. 97.
M. Płachta, M. Krzemień, K. Szczypiorski, and A. Janicki, "Detection of Image Steganography Using Deep Learning and Ensemble Classifiers," Electronics, vol. 11, no. 10, May 2022, Art. no. 1565.
A. Kouhi and M. H. Sedaaghi, "Prediction error distribution with dynamic asymmetry for reversible data hiding," Expert Systems with Applications, vol. 184, Dec. 2021, Art. no. 115475.
C.-C. Chang, X. Wang, S. Chen, I. Echizen, V. Sanchez, and C.-T. Li, "Deep Learning for Predictive Analytics in Reversible Steganography," IEEE Access, vol. 11, pp. 3494–3510, 2023.
Y. Li, B. Ling, D. Hu, S. Zheng, and G. Zhang, "A Deep Learning Driven Feature Based Steganalysis Approach," Intelligent Automation & Soft Computing, vol. 37, no. 2, pp. 2213–2225, June 2023.
T. K. Alshekly, E. A. AlBahrani, and L. B. Ayed, "Code-Based Cryptography and Chaotic Maps as Pseudo-Random Bit Generator," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29041–29048, Dec. 2025.
A. Gutub and F. Al-Shaarani, "Efficient Implementation of Multi-image Secret Hiding Based on LSB and DWT Steganography Comparisons," Arabian Journal for Science and Engineering, vol. 45, no. 4, pp. 2631–2644, Apr. 2020.
S. Alharthi and A. Gutub, "Adjusting image stego practicality via YCbCr color space formation," Journal of Engineering Research, vol. 14, no. 1, pp. 756–764, Mar. 2026.
F. S. Hassan and A. Gutub, "Efficient reversible data hiding multimedia technique based on smart image interpolation," Multimedia Tools and Applications, vol. 79, no. 39, pp. 30087–30109, Oct. 2020.
Z. Saeidi, A. Yazdi, S. Mashhadi, M. Hadian, and A. Gutub, "High performance image steganography integrating IWT and Hamming code within secret sharing," IET Image Processing, vol. 18, no. 1, pp. 129–139, Jan. 2024.
A. Aljarf, H. Zamzami, and A. Gutub, "Integrating machine learning and features extraction for practical reliable color images steganalysis classification," Soft Computing, vol. 27, no. 19, pp. 13877–13888, Oct. 2023.
J. Hemalatha, M. Sekar, C. Kumar, A. Gutub, and A. K. Sahu, "Towards improving the performance of blind image steganalyzer using third-order SPAM features and ensemble classifier," Journal of Information Security and Applications, vol. 76, Aug. 2023, Art. no. 103541.
F. S. Hassan and A. Gutub, "Improving data hiding within colour images using hue component of HSV colour space," CAAI Transactions on Intelligence Technology, vol. 7, no. 1, pp. 56–68, Mar. 2022.
A. Aljarf, H. Zamzami, and A. Gutub, "Is blind image steganalysis practical using feature-based classification?," Multimedia Tools and Applications, vol. 83, no. 2, pp. 4579–4612, Jan. 2024.
A. Saini and R. Sehrawat, "Enhancing Data Security through Machine Learning-based Key Generation and Encryption," Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14148–14154, June 2024.
Abhishek and R. Sehrawat, "Sustainable Image-based Encryption Using Cryptography and Steganography with Autoencoder," in Proceedings of 4th International Conference on ICT for Digital, Smart, and Sustainable Development, Delhi, India, 2024, pp. 205–214.
U. Rawat, Abhishek, H. Singh, and A. Ur Rehman, "Cybersecurity Challenges and Risks in AGI Development and Deployment," in Artificial General Intelligence (AGI) Security: Smart Applications and Sustainable Technologies, S. El Hajjami, K. Kaushik, and I. U. Khan, Eds. Singapore: Springer Nature, 2025, pp. 291–314.
J. Zhu, R. Kaplan, J. Johnson, and L. Fei-Fei, "HiDDeN: Hiding Data With Deep Networks," in 15th European Conference on Computer Vision, Munich, Germany, 2018, pp. 682–697.
K. A. Zhang, A. Cuesta-Infante, L. Xu, and K. Veeramachaneni, "SteganoGAN: High Capacity Image Steganography with GANs." arXiv, Jan. 30, 2019.
Z. Wang, M. Zhou, B. Liu, and T. Li, "Deep Image Steganography Using Transformer and Recursive Permutation," Entropy, vol. 24, no. 7, June 2022, Art. no. 878.
"Steganography datasets and tools." DDE Lab, Binghamton University. https://dde.binghamton.edu/download/.
Downloads
How to Cite
License
Copyright (c) 2026 R. Padma, Vamsidhar Yendapalli
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
