Skip to main content
Springer Nature Link
Log in

FPFnet: Image steganalysis model based on adaptive residual extraction and feature pyramid fusion

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Image steganalysis is a technique for detecting images that contain hidden information. Convolutional neural networks have shown great potential in the steganalysis field. In this paper, we propose the feature pyramid fusion network (FPFnet), an image steganalysis model that combines adaptive residual extraction and feature pyramid fusion. In pre-processing, we present an adaptive residual extraction method instead of manually designed filters for extracting diverse residual features. The residual calculation function is reformed to improve the stability of optimal parameters. The residual is adaptively scaled to improve the truncation process. The residual extraction and truncation processes are incorporated into network training. To improve the utilization of residual features in different layers, we design feature pyramid fusion structure by introducing up sampling and feature fusion methods to fuse residual maps of different sizes in neural networks. Comparative experiments with different residual extraction methods, as well as up sampling and feature fusion methods, show that FPFnet has higher accuracy than other steganalysis models on the spatial universal wavelet relative distortion (S-UNIWARD) and wavelet obtained weights (WOW) datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data availability

The steganography algorithm code and BOSSBase version 1.01 data used to support the findings of this study are available in the Binghamton repository at http://dde.binghamton.edu/download/.

References

  1. Li B, He J, Huang J et al (2011) A survey on image steganography and steganalysis. J Inf Hiding Multim Signal Process 2:142–172

    Google Scholar 

  2. Cheddad A, Condell J, Curran K et al (2010) Digital image steganography: Survey and analysis of current methods. Signal Process 90:727–752

    Article  Google Scholar 

  3. Kadhim IJ, Premaratne P, Vial PJ et al (2019) Comprehensive survey of image steganography: Techniques, Evaluations, and trends in future research. Neurocomputing 335:299–326

    Article  Google Scholar 

  4. Filler T, Judas J, Fridrich J (2011) Minimizing Additive Distortion in Steganography Using Syndrome-Trellis Codes. IEEE Trans Inf Forensics Secur 6:920–935

    Article  Google Scholar 

  5. Filler T, Fridrich J (2010) Gibbs construction in steganography. IEEE Trans Inf Forensics Secur 5:705–720

  6. Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: 2012 IEEE International Workshop on Information Forensics and Security (WIFS). pp 234–239

  7. Holub V, Fridrich J, Denemark T (2014) Universal distortion function for steganography in an arbitrary domain. EURASIP J Inf Secur 2014:1–13

    Article  Google Scholar 

  8. Kodovský J, Fridrich J (2011) Steganalysis in high dimensions: fusing classifiers built on random subspaces. In: Media Watermarking, Security, and Forensics III. SPIE, pp 204–216

  9. Fridrich J, Kodovsky J (2012) Rich Models for Steganalysis of Digital Images. IEEE Trans Inf Forensics Secur 7:868–882

    Article  Google Scholar 

  10. JaK S, Vandewalle J (1999) Least Squares Support Vector Machine Classifiers. Neural Process Lett 9:293–300

    Article  Google Scholar 

  11. Kodovsky J, Fridrich J, Holub V (2012) Ensemble Classifiers for Steganalysis of Digital Media. IEEE Trans Inf Forensics Secur 7:432–444

    Article  Google Scholar 

  12. Kodovský J, Fridrich J (2012) Steganalysis of JPEG images using rich models. In: Media Watermarking, Security, and Forensics 2012. SPIE, pp 81–93

  13. Holub V, Fridrich J (2013) Random Projections of Residuals for Digital Image Steganalysis. IEEE Trans Inf Forensics Secur 8:1996–2006

    Article  Google Scholar 

  14. Denemark T, Sedighi V, Holub V et al (2014) Selection-channel-aware rich model for Steganalysis of digital images. In: 2014 IEEE International Workshop on Information Forensics and Security (WIFS). pp 48–53

  15. Selvaraj A, Ezhilarasan A, Wellington SLJ et al (2021) Digital image steganalysis: A survey on paradigm shift from machine learning to deep learning based techniques. IET Image Process 15:504–522

    Article  Google Scholar 

  16. Tan S, Li B (2014) Stacked convolutional auto-encoders for steganalysis of digital images. In: Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific. pp 1–4

  17. Qian Y, Dong J, Wang W et al (2015) Deep learning for steganalysis via convolutional neural networks. In: Media Watermarking, Security, and Forensics 2015. SPIE, pp 171–180

  18. Xu G, Wu H-Z, Shi Y-Q (2016) Structural Design of Convolutional Neural Networks for Steganalysis. IEEE Signal Process Lett 23:708–712

    Article  Google Scholar 

  19. Ye J, Ni J, Yi Y (2017) Deep Learning Hierarchical Representations for Image Steganalysis. IEEE Trans Inf Forensics Secur 12:2545–2557

    Article  Google Scholar 

  20. Yedroudj M, Comby F, Chaumont M (2018) Yedroudj-Net: an efficient CNN for spatial steganalysis. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp 2092–2096

  21. Boroumand M, Chen M, Fridrich J (2019) Deep Residual Network for Steganalysis of Digital Images. IEEE Trans Inf Forensics Secur 14:1181–1193

    Article  Google Scholar 

  22. Zhang R, Zhu F, Liu J et al (2020) Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis. IEEE Trans Inf Forensics Secur 15:1138–1150

    Article  Google Scholar 

  23. Pevny T, Bas P, Fridrich J (2010) Steganalysis by Subtractive Pixel Adjacency Matrix. IEEE Trans Inf Forensics Secur 5:215–224

    Article  Google Scholar 

  24. Li B, Wei W, Ferreira A et al (2018) ReST-Net: Diverse Activation Modules and Parallel Subnets-Based CNN for Spatial Image Steganalysis. IEEE Signal Process Lett 25:650–654

    Article  Google Scholar 

  25. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 770–778

  26. Szegedy C, Ioffe S, Vanhoucke V et al (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 4278–4284

  27. He K, Zhang X, Ren S et al (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Trans Pattern Anal Mach Intell 37:1904–1916

    Article  Google Scholar 

  28. You WK, Zhang H, Zhao XF (2021) A Siamese CNN for Image Steganalysis. IEEE Trans Inf Forensics Secur 16:291–306

    Article  Google Scholar 

  29. Tan SQ, Wu WL, Shao ZL et al (2021) CALPA-NET: Channel-Pruning-Assisted Deep Residual Network for Steganalysis of Digital Images. IEEE Trans Inf Forensics Secur 16:131–146

    Article  Google Scholar 

  30. Weng S, Chen M, Yu L et al (2022) Lightweight and Effective Deep Image Steganalysis Network. IEEE Signal Process Lett 29:1888–1892

    Article  Google Scholar 

  31. Xie G, Ren J, Marshall S et al (2023) Self-attention enhanced deep residual network for spatial image steganalysis. Digital Signal Processing 139:104063

    Article  Google Scholar 

  32. Wu T, Wang L, Zhai L et al (2022) Progressive selection-channel networks for image steganalysis. Int J Intell Syst 37:7444–7458

    Article  Google Scholar 

  33. Chen H, Han Q, Li Q et al (2023) Image steganalysis with multi-scale residual network. Multimed Tools App 82:22009–22031

    Article  Google Scholar 

  34. Sutskever I, Martens J, Dahl G et al (2013) On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning. pp 1139–1147

  35. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning. pp 448–456

  36. Lin T-Y, Dollár P, Girshick R et al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 2117–2125

  37. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. pp 234–241

  38. Lin M, Chen Q, Yan S (2013) Network in network. arXiv preprint arXiv:1312.4400

  39. Bas P, Filler T, Pevný T (2011) “Break Our Steganographic System”: The Ins and Outs of Organizing BOSS. In: Springer Berlin Heidelberg. pp 59–70

  40. He K, Zhang X, Ren S et al (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV). pp 1026–1034

  41. Xueyi Y, Wenfeng G, Maosheng Z et al (2022) Image Steganography Detection Based on Multilayer Perceptual Convolution and Channel Weighting. J Electron Inf Technol 44:1–8

    Google Scholar 

  42. Amrutha E, Arivazhagan S, Sylvia Lilly Jebarani W (2022) MixNet: A Robust Mixture of Convolutional Neural Networks as Feature Extractors to Detect Stego Images Created by Content-Adaptive Steganography. Neural Process Lett 54:853–870

    Article  Google Scholar 

  43. Xu GY, Xu Y, Zhang SC et al (2021) SFRNet: Feature Extraction-Fusion Steganalysis Network Based on Squeeze-and-Excitation Block and RepVgg Block. Secur Commun Netw 2021:3676720

    Article  Google Scholar 

Download references

Acknowledgements

This study was supported by the National Natural Science Foundation of China (61876189)

Funding

National Natural Science Foundation of China, Grant/Award Numbers (61876189).

Author information

Authors and Affiliations

  1. Air Force Engineering University, Xi’an, China

    Li Jingtai, Wang Xiaodan, Song Yafei & Wang Peng

Authors
  1. Li Jingtai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wang Xiaodan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Song Yafei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wang Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wang Xiaodan.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, J., Wang, X., Song, Y. et al. FPFnet: Image steganalysis model based on adaptive residual extraction and feature pyramid fusion. Multimed Tools Appl 83, 48539–48561 (2024). https://doi.org/10.1007/s11042-023-17592-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-17592-z

Keywords