Edge-Guided Dual-Stream U-Net for Secure Image Steganography
Source abstract
Abstract
Steganography, a technique for concealing information, often faces challenges such as low decoding accuracy and inadequate extraction of edge and global features. To overcome these limitations, we propose a dual-stream U-Net framework with integrated edge enhancement for image steganography. Our main contributions include the adoption of a dual-stream U-Net structure in the encoder, integrating an edge-enhancement stream with the InceptionDMK module for multi-scale edge detail extraction, and incorporating a multi-scale median attention (MSMA) module into the original input stream to enhance feature representation. This dual-stream design promotes deep feature fusion, thereby improving the edge details and embedding capacity of stego images. Moreover, an iterative optimization strategy is employed to progressively refine the selection of cover images and the embedding process, achieving enhanced stego quality and decoding performance. Experiments show that our method produces high-quality stego images across multiple public datasets, achieving near-100% decoding accuracy. It also surpasses existing methods in visual quality metrics like PSNR and SSIM. This framework offers a promising approach for enhancing steganographic security in real-world applications such as secure communication and data protection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Steganography and Watermarking Techniques · Digital Media Forensic Detection · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer and Information Engineering (College of Artificial Intelligence), Nanjing Tech University, Nanjing 211816, China
References (50)
Show source-provided references
1. Hybrid data encryption model integrating multi-objective adaptive genetic algorithm for secure medical data communication over cloud-based healthcare systems10.1007/s11042-021-10723-4 ↗
2. A novel coverless information hiding method based on the most significant bit of the cover image10.1109/ACCESS.2020.3000993 ↗
3. Exploring steganography: Seeing the unseen10.1109/MC.1998.4655281 ↗
4. A steganographic method for images by pixel-value differencing10.1016/S0167-8655(02)00402-6 ↗
5. Ramkumar, M., Akansu, A.N., and Alatan, A. (1999, January 24–28). A robust data hiding scheme for images using DFT. Proceedings of the International Conference on Image Processing, Kobe, Japan.
6. Steganographic approach for hiding image in DCT domain
7. A DWT based approach for image steganography
8. Minimizing additive distortion in steganography using syndrometrellis codes10.1109/TIFS.2011.2134094 ↗
9. Pevný, T., Filler, T., and Bas, P. (2010, January 28–30). Using high-dimensional image models to perform highly undetectable steganography. Proceedings of the International Workshop on Information Hiding, Calgary, AB, Canada.10.1007/978-3-642-16435-4_13 ↗
10. Holub, V., and Fridrich, J. (2012, January 2–5). Designing steganographic distortion using directional filters. Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security (WIFS), Costa, Adeje, Spain.10.1109/WIFS.2012.6412655 ↗
11. Holub, V., and Fridrich, J. (2013, January 17–19). Digital image steganography using universal distortion. Proceedings of the First ACM Workshop on Information Hiding and Multimedia Security, Montpellier, France.10.1145/2482513.2482514 ↗
12. Hiding images in plain sight: Deep steganography
13. Zhu, J., Kaplan, R., Johnson, J., and Fei-Fei, L. (2018, January 8–14). HiDDeN: Hiding data with deep networks. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01267-0_40 ↗
14. Reversible image steganography scheme based on a U-Net structure10.1109/ACCESS.2019.2891247 ↗
15. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
16. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
17. Zhang, K.A., Cuesta-Infante, A., Xu, L., and Veeramachaneni, K. (2019). Steganogan High capacity image steganography with gans. arXiv.
18. Channel attention image steganography with generative adversarial networks10.1109/TNSE.2021.3139671 ↗
19. Chen, X., Kishore, V., and Weinberger, K.Q. (2022, January 1–5). Learning iterative neural optimizers for image steganography. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda.
20. Westfeld, A., and Pfitzmann, A. (1999). Attacks on Steganographic Systems International Work·50·Shop on Information Hiding, Springer.10.1007/10719724_5 ↗
21. Jessica, F., Goljan, M., and Du, R. (2001, January 5). Reliable detection of LSB steganography in color and grayscale images. Proceedings of the 2001 Workshop on Multimedia and Security: New Challenges, Ottawa, ON, Canada.
22. Westfeldt, A. (2001, January 25–27). F5–a steganographic algorithm. Proceedings of the International Workshop on Information Hiding, Pittsburgh, PA, USA.10.1007/3-540-45496-9_21 ↗
23. Image steganographic scheme based on pixel-value differencing and LSB replacement methods10.1049/ip-vis:20059022 ↗
24. A high quality steganographic method with pixel-value differencing and modulus function10.1016/j.jss.2007.01.049 ↗
25. Data embedding using pixel value differencing and diamond encoding with multiple-base notational system10.1016/j.jss.2011.12.045 ↗
26. Investigation on cost assignment in spatial image steganography10.1109/TIFS.2014.2326954 ↗
27. Hayes, J., and Danezis, G. (2017, January 4–9). Generating steganographic images via adversarial training. Proceedings of the NIPS, Long Beach, CA, USA.
28. HCISNet: Higher capacity invisible image steganographic network10.1049/ipr2.12329 ↗
29. Zhang, S., Li, H., Lim, L., Lu, J., and Zuo, Z. (2022). A high-capacity steganography algorithm based on adaptive frequency channel attention networks. Sensors, 22.10.3390/s22207844 ↗
30. Jing, J., Deng, X., Xu, M., Wang, J., and Guan, Z. (2021, January 11–17). Hinet: Deep image hiding by invertible network. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00469 ↗
31. Kishore, V., Chen, X., Wang, Y., Li, B., and Weinberger, K.Q. (2022, January 25–29). Fixed Neural Network Steganography: Train the Images, Not the Network. Proceedings of the International Conference on Learning Representations (ICLR), Virtual.
32. Bui, T., Agarwal, S., Yu, N., and Collomosse, J. (2023, January 18–22). RoSteALS: Robust Steganography using Autoencoder Latent Space. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.10.1109/CVPRW59228.2023.00100 ↗
33. E-SEVSR—Edge Guided Stereo Endoscopic Video Super-Resolution10.1109/ACCESS.2024.3367980 ↗
34. A survey on Deep-Learning-based image steganography10.1016/j.eswa.2024.124390 ↗
35. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
36. Squeeze & Excitation joint with Combined Channel and Spatial Attention for Pathology Image Super-Resolution10.1016/j.fraope.2024.100170 ↗
37. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
38. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 8–22). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
39. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
40. Agustsson, E., and Timofte, R. (2017, January 21–26). NTIRE 2017 challenge on single image superresolution: Dataset and study. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA.10.1109/CVPRW.2017.150 ↗
41. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll, P., and Zitnick, C.L. (2014, January 6–12). Microsoft coco: Common objects in context. Proceedings of the European Conference on Computer Vision, Zürich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
42. Large-scale celebfaces attributes (celeba) dataset
43. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
44. Ponomarenko, N., Ieremeiev, O., Lukin, V., Egiazarian, K., Jin, L., Astola, J., Vozel, B., Chehdi, K., Carli, M., and Battisti, F. (2013, January 10–12). Color image database TID2013: Peculiarities and preliminary results. Proceedings of the European Workshop on Visual Information Processing (EUVIP), Paris, France.
45. FSIM: A Feature Similarity Index for Image Quality Assessment10.1109/TIP.2011.2109730 ↗
46. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
47. Structural design of convolutional neural networks for steganalysis10.1109/LSP.2016.2548421 ↗
48. Deep learning hierarchical representations for image steganalysis10.1109/TIFS.2017.2710946 ↗
49. Deep residual network for steganalysis of digital images10.1109/TIFS.2018.2871749 ↗
50. Yedroudj, M., Comby, F., and Chaumont, M. (2018, January 15–20). Yedroudj-Net: An Efficient CNN for Spatial Steganalysis. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461438 ↗