International Journal of Engineering

International Journal of Engineering

VidaFormer: A Hybrid Transformer for Image Steganography

Document Type : Original Article

Authors
V. Yousefi Ramandi
M. Fateh
M. Rezvani
Faculty of Computer Engineering, Shahrood University of Technology, Shahrood, Iran
10.5829/ije.2026.39.10a.07
Abstract
Image steganography has advanced significantly with the integration of deep learning, particularly through the use of convolutional neural networks (CNNs) for extracting complex features. While CNNs have long been a cornerstone of image analysis due to their efficiency in capturing local dependencies, the emergence of transformer models has revolutionized the field by achieving superior accuracy and effectively capturing global relationships within data. Transformers encounter issues with computational expense and memory consumption, especially when handling high-resolution images. To address these limitations, we propose a hybrid architecture that uses convolutional layers in high-resolution stages and transformer blocks in low-resolution stages. This design balances efficiency and performance by leveraging convolutional layers to capture short-range dependencies and transformers to model long-range relationships. Additionally, by replacing standard convolutions with CoordConv layers, we enhance the model's spatial awareness and feature localization capabilities. We introduce VidaFormer, an innovative steganography framework that integrates deep learning with these architectural enhancements to embed arbitrary binary data into images while maintaining high visual quality in the resulting stego images. VidaFormer outperforms state-of-the-art models, achieving an effective capacity of 4.89 bits-per-pixel on the DIV2K dataset, a 1.7% improvement over the previous best model. This demonstrates VidaFormer's superior performance and scalability for modern image steganography applications. 

Graphical Abstract

VidaFormer: A Hybrid Transformer for Image Steganography
Keywords
Image Steganography
Information Hiding
Deep Learning
Convolution
Transformers

Subjects

1.    You Z, Ying Q, Li S, Qian Z, Zhang X, editors. Image generation network for covert transmission in online social network. Proceedings of the 30th ACM International Conference on Multimedia; 2022. DOI: 10.1145/3503161.3548139. 
2.    Evsutin O, Melman A, Meshcheryakov R. Digital Steganography and Watermarking for Digital Images: A Review of Current Research Directions. IEEE Access. 2020;8:166589-611. DOI: 10.1109/ACCESS.2020.3022779. 
3.    Saadati M, Vahidi J, Seydi V, Sheikholharam Mashhadi P. Proposing a New Image Watermarking Method Using Shearlet Transform and Whale Optimization Algorithm. International Journal of Engineering Transactions A: Basics. 2021;34(4):843-53. DOI: 10.5829/ije.2021.34.04a.10. 
4.    Qi Y, Chen K, Zhao N, Yang Z, Zhang W. Provably Secure Robust Image Steganography via Cross-Modal Error Correction. arXiv e-prints. 2024:arXiv: 2412.12206. DOI: 10.48550/arXiv.2412.12206. 
5.    Luo Z, Li S, Li G, Qian Z, Zhang X, editors. Securing Fixed Neural Network Steganography. Proceedings of the 31st ACM International Conference on Multimedia; 2023. DOI: 10.1145/3581783.3611920.
6.    Fateh M, Mohsen  R, Yasser  I. A new method of coding for steganography based on LSB matching revisited. Security and Communication Networks. 2021:1-15. DOI: 10.1155/2021/6610678. 
7.    Mielikainen J. LSB matching revisited. IEEE signal processing letters. 2006;13(5):285-7. DOI: 10.1109/LSP.2006.870357. 
8.    Duan X, Liu N, Gou M, Wang W, Qin C. SteganoCNN: Image steganography with generalization ability based on convolutional neural network. Entropy. 2020;22(10):1140. DOI: 10.3390/e22101140. 
9.    Kumar V, Laddha S, Aniket ND. Steganography techniques using convolutional neural networks. J Homepage. 2020;7:66-73. DOI: 10.18280/rces.070304. 
10.    Wu P, Yang Y, Li X, editors. Image-into-image steganography using deep convolutional network. Advances in Multimedia Information Processing–PCM 2018: 19th Pacific-Rim Conference on Multimedia, Hefei, China, September 21-22, 2018, Proceedings, Part II 19; 2018: Springer. DOI: 10.1007/978-3-030-00767-6_73. 
11.    Ronneberger O, Fischer P, Brox T, editors. U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical image computing and computer-assisted intervention; 2015. DOI: 10.1007/978-3-319-24574-4_28.
12.    Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H, editors. CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops; 2020. DOI: 10.1109/CVPRW50498.2020.00203.
13.    Huang G, Liu Z, Van Der Maaten L, Weinberger KQ, editors. Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition; 2017. DOI: 10.1016/j.patcog.2020.107610
14.    Luo W, Li Y, Urtasun R, Zemel R. Understanding the effective receptive field in deep convolutional neural networks. Advances in neural information processing systems. 2016;29. DOI: 10.5555/3157382.3157645. 
15.    Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al., editors. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations; 2020. DOI: 10.48550/arXiv.2010.11929.
16.    Vaswani A. Attention is all you need. Advances in Neural Information Processing Systems. 2017. DOI: 10.5555/3295222.3295349. 
17.    Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al., editors. Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE/CVF international conference on computer vision; 2021. DOI: 10.1109/ICCV48922.2021.00986.
18.    Liu Z, Hu H, Lin Y, Yao Z, Xie Z, Wei Y, et al., editors. Swin transformer v2: Scaling up capacity and resolution. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2022. DOI: 10.1109/CVPR52688.2022.01170.
19.    Dong X, Bao J, Chen D, Zhang W, Yu N, Yuan L, et al., editors. Cswin transformer: A general vision transformer backbone with cross-shaped windows. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2022. DOI: 10.1109/CVPR52688.2022.01181.
20.    Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, et al. A survey on vision transformer. EEE transactions on pattern analysis and machine intelligence. 2022;45(1):87-110. DOI: 10.1109/TPAMI.2022.3152247. 
21.    Kayhan OS, Gemert JCv, editors. On translation invariance in cnns: Convolutional layers can exploit absolute spatial location. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2020. DOI: 10.1109/CVPR42600.2020.01428.
22.    Liu R, Lehman J, Molino P, Petroski Such F, Frank E, Sergeev A, et al. An intriguing failing of convolutional neural networks and the coordconv solution. Advances in neural information processing systems. 2018;31. DOI: 10.5555/3327546.3327630. 
23.    Reed IS, Solomon G. Polynomial codes over certain finite fields. Journal of the society for industrial and applied mathematics. 1960;8(2):300-4. DOI: 10.1137/0108018. 
24.    Fateh M, Rezvani M, Irani Y. A New Method of Coding for Steganography Based on LSB Matching Revisited. Security and Communication Networks. 2021;2021(1):6610678. 10.1155/2021/6610678. 
25.    Karim SM, Rahman MS, Hossain MI, editors. A new approach for LSB based image steganography using secret key. 14th international conference on computer and information technology (ICCIT 2011); 2011: IEEE. DOI: 10.1109/ICCITechn.2011.6164800.
26.    mansoor fateh sr, elahe alipour. Review of Image Steganography Based on LSB and Pixel Classification and Providing a New Method in This Area. Biannual Journal Monadi for Cyberspace Security (AFTA). 2017;5(2):9. http://monadi.isc.org.ir/article-1-82-en.html.  
27.    Singh A, Singh H, editors. An improved LSB based image steganography technique for RGB images. 2015 IEEE International Conference on electrical, computer and communication technologies (ICECCT); 2015: IEEE. DOI: 10.1109/ICECCT.2015.7226122.
28.    Das R, Tuithung T, editors. A novel steganography method for image based on Huffman Encoding. 2012 3rd National Conference on Emerging Trends and Applications in Computer Science; 2012: IEEE. DOI: 10.1109/NCETACS.2012.6203290. 
29.    Arham A, Nugroho HA. Enhanced reversible data hiding using difference expansion and modulus function with selective bit blocks in images. Cybersecurity. 2024;7(1):61. DOI: 10.1186/s42400-024-00251-7. 
30.    Chhajed G, Garg B. Novel Scheme for Data Hiding in Binary Images using Cover Pattern Histogram. International Journal of Engineering Transactions B: Applications. 2023;36(11):2124-36. DOI: 10.5829/ije.2023.36.11b.16. 
31.    Alexan W, Mamdouh E, Aboshousha A, Alsahafi YS, Gabr M, Hosny KM. Stegocrypt: A robust tri‐stage spatial steganography algorithm using TLM encryption and DNA coding for securing digital images. IET Image Processing. 2024;18(13):4189-206. DOI: 10.1049/ipr2.13242. 
32.    Qu Z, Cheng Z, Liu W, Wang X. A novel quantum image steganography algorithm based on exploiting modification direction. Multimedia Tools and Applications. 2019;78:7981-8001. DOI: 10.1007/s11042-018-6476-5. 
33.    Wang S, Sang J, Song X, Niu X. Least significant qubit (LSQb) information hiding algorithm for quantum image. Measurement. 2015;73:352-9. DOI: 10.1016/j.measurement.2015.05.038. 
34.    Swain G. Very high capacity image steganography technique using quotient value differencing and LSB substitution. Arabian Journal for Science and Engineering. 2019;44(4):2995-3004. DOI: 10.1007/s13369-018-3372-2. 
35.    Qiu A, Chen X, Sun X, Wang S, Guo W. Coverless image steganography method based on feature selection. Journal of Information Hiding and Privacy Protection. 2019;1(2):49. DOI: 10.32604/jihpp.2019.05881. 
36.    Butora J, Puteaux P, Bas P. Errorless robust JPEG steganography using outputs of JPEG coders. IEEE Transactions on Dependable and Secure Computing. 2023. DOI: 10.1109/TDSC.2023.3306379. 
37.    Bhatia SS, Singh K, Kasana G. Singular Value Decomposition based Steganography Technique for JPEG2000 Compressed Images. International Journal of Engineering Transactions C: Aspects. 2015;28(12):1720-7. DOI: 10.5829/idosi.ije.2015.28.12c.04. 
38.    Wu P, Yang Y, Li X. Stegnet: Mega image steganography capacity with deep convolutional network. Future Internet. 2018;10(6):54. DOI: 10.3390/fi10060054. 
39.    Duan X, Jia K, Li B, Guo D, Zhang E, Qin C. Reversible image steganography scheme based on a U-Net structure. IEEE Access. 2019;7:9314-23. DOI: 10.1109/ACCESS.2019.2891247. 
40.    Rahim R, Nadeem S, editors. End-to-end trained CNN encoder-decoder networks for image steganography. Proceedings of the European conference on computer vision (ECCV) workshops; 2018. DOI: 10.1007/978-3-030-11018-5_64.
41.    Wang Z, Gao N, Wang X, Xiang J, Liu G, editors. STNet: A style transformation network for deep image steganography. Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part II 26; 2019: Springer. DOI: 10.1007/978-3-030-36711-4_1.
42.    Simonyan K, Zisserman A, editors. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations (ICLR 2015); 2015: Computational and Biological Learning Society. 
43.    Baluja S. Hiding images in plain sight: Deep steganography. Advances in neural information processing systems. 2017;30. DOI: 10.5555/3294771.3294968. 
44.    Zhou Z, Su Y, Li J, Yu K, Wu QJ, Fu Z, et al. Secret-to-image reversible transformation for generative steganography. IEEE Transactions on Dependable and Secure Computing. 2022;20(5):4118-34. DOI: 10.1109/TDSC.2022.3217661. 
45.    Zhang J, Chen K, Li W, Zhang W, Yu N. Steganography with Generated Images: Leveraging Volatility to Enhance Security. IEEE Transactions on Dependable and Secure Computing. 2023. DOI: 10.1109/TDSC.2023.3341427. 
46.    Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Advances in neural information processing systems. 2014;27. DOI: 10.5555/2969033.2969125. 
47.    Volkhonskiy D, Borisenko B, Burnaev E. Generative adversarial networks for image steganography. 2016.  
48.    Volkhonskiy D, Nazarov I, Burnaev E, editors. Steganographic generative adversarial networks. Twelfth international conference on machine vision (ICMV 2019); 2020: SPIE. DOI: 10.1117/12.2559429.
49.    Ramandi VY, Fateh M, Rezvani M. VidaGAN: Adaptive GAN for image steganography. IET Image Processing. 2024;18(12):3329-42. DOI: 10.1049/ipr2.13177.
50.    Zhang KA, Cuesta-Infante A, Xu L, Veeramachaneni K. SteganoGAN: High Capacity Image Steganography with GANs. ArXiv. 2019;abs/1901.03892. DOI: 10.48550/arXiv.1901.03892.
51.    Bi X, Yang X, Wang C, Liu J. High-Capacity Image Steganography Algorithm Based on Image Style Transfer. Security and Communication Networks. 2021;2021(1):4179340. DOI: 10.1155/2021/4179340.  
52.    Su W, Ni J, Sun Y. StegaStyleGAN: towards generic and practical generative image steganography.  Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence: AAAI Press; 2024. p. Article 28. DOI: 10.1609/aaai.v38i1.27776 
53.    Tang W, Rao Y, Yang Z, Peng F, Cui X, Huang J, et al. Reversible generative steganography with distribution-preserving. Cybersecurity. 2025;8(1):18. DOI: 10.1186/s42400-024-00317-6.  
54.    Wang Z, Zhou M, Liu B, Li T. Deep Image Steganography Using Transformer and Recursive Permutation. Entropy. 2022;24(7):878. DOI: 10.3390/e24070878.  
55.    Zhou Y, Luo T, He Z, Jiang G, Xu H, Chang C-C. CAISFormer: Channel-wise attention transformer for image steganography. Neurocomputing. 2024;603:128295. DOI: 10.1016/j.neucom.2024.128295. 
56.    Xiao C, Peng S, Zhang L, Wang J, Ding D, Zhang J. A transformer-based adversarial network framework for steganography. Expert Systems with Applications. 2025;269:126391. DOI: 10.1016/j.eswa.2025.126391. 
57.    Zhou W, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing. 2004;13(2):600-12. DOI: 10.1109/TIP.2003.819861. 
58.    Setiadi DRIM. PSNR vs SSIM: imperceptibility quality assessment for image steganography. Multimedia Tools and Applications. 2021;80(6):8423-44. DOI: 10.1007/s11042-020-10035-z. 
59.    Agustsson E, Timofte R. NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study.  2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): IEEE Computer Society; 2017. p. 1122-31. DOI: 10.1109/cvprw.2017.150. 
60.    Kinga D, Adam JB, editors. A method for stochastic optimization. International conference on learning representations (ICLR); 2015: California;. 
61.    Mehta, S., & Rastegari, M. MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. ArXiv. 2021;   DOI: 10.48550/arXiv.2110.02178.
62.    Kishore V, Chen X, Wang Y, Li B, Weinberger KQ, editors. Fixed neural network steganography: Train the images, not the network. International Conference on Learning Representations; 2021. 
63.    Zhang S, Li H, Li L, Lu J, Zuo Z. A high-capacity steganography algorithm based on adaptive frequency channel attention networks. Sensors. 2022;22(20):7844. DOI: 10.3390/s22207844. 
64.    Chen X, Kishore V, Weinberger KQ, editors. Learning iterative neural optimizers for image steganography. The Eleventh International Conference on Learning Representations; 2023. https://openreview.net/forum?id=gLPkzWjdhBN. 
65.    Reinel T-S, Brayan A-AH, Alejandro B-OM, Alejandro M-R, Daniel A-G, Alejandro A-GJ, et al. GBRAS-Net: A convolutional neural network architecture for spatial image steganalysis. IEEE Access. 2021;9:14340-50. DOI: 10.1109/ACCESS.2021.3052494. 
International Journal of Engineering
Volume 39, Issue 10
TRANSACTIONS A: Basics
October 2026
Pages 2434-2451