SpringerLink
Log in

Multi-contextual design of convolutional neural network for steganalysis

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

Abstract

In recent times, deep learning-based steganalysis classifiers have become popular due to their state-of-the-art performance. Most deep steganalysis classifiers usually extract noise residuals using high-pass filters as preprocessing steps and feed them to their deep model for classification. It is observed that recent steganographic embedding does not always restrict their embedding in the high-frequency zone; instead, they distribute it as per embedding policy. Therefore, besides noise residual, learning the embedding zone is another challenging task. In this work, unlike the conventional approaches, the proposed model first extracts the noise residual using learned denoising kernels to boost the signal-to-noise ratio. After preprocessing, the sparse noise residuals are fed to a novel Multi-Contextual Convolutional Neural Network (M-CNET) that uses heterogeneous context size to learn the sparse and low-amplitude representation of noise residuals. The model performance is further improved by incorporating the Self-Attention module to focus on the areas prone to steganalytic embedding. A set of comprehensive experiments is performed to show the proposed scheme’s efficacy over the prior arts. Besides, an ablation study is given to justify the contribution of various modules of the proposed architecture.

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
EUR 32.99 /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 includes VAT (Germany)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. KV filter can be found in [36] in (2).

  2. The code for steganography algorithms are downloaded from http://dde.binghamton.edu/download/stego_algorithms/

  3. code to compute WAUC is downloaded from: https://www.kaggle.com/c/alaska2-image-steganalysis/overview/evaluation

  4. Imagenet images are first converted to grayscale using rgb2gray and then resized to \(256\times 256\) using imresize function of Matlab before the embedding.

References

  1. Bas P, Filler T, Pevnỳ T (2011) “break our steganographic system”: the ins and outs of organizing boss. In: International workshop on information hiding. Springer, pp 59–70

  2. Bas P, Furon T (2007) Bows-2 (2007). Software available from:\(\{\)http://bows2. gipsa-lab. inpg. fr\(\}\)

  3. Bengio Y (2012) Deep learning of representations for unsupervised and transfer learning. In: Proceedings of ICML workshop on unsupervised and transfer learning. pp 17–36

  4. Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems. pp 153–160

  5. Boroumand M, Chen M, Fridrich J (2018) Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensic Secur 14(5):1181–1193

    Article  Google Scholar 

  6. Cogranne R, Giboulot Q, Bas P (2020) ALASKA-2: challenging academic research on steganalysis with realistic images. In: IEEE international workshop on information forensics and security

  7. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255

  8. Drucker H, Burges CJ, Kaufman L, Smola AJ, Vapnik V (1997) Support vector regression machines. In: Advances in neural information processing systems. pp 155–161

  9. Filler T, Fridrich J (2010) Gibbs construction in steganography. IEEE Trans Inf Forensic Secur 5(4):705–720

    Article  Google Scholar 

  10. Filler T, Judas J, Fridrich J (2011) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inf Forensic Secur 6(3):920–935

    Article  Google Scholar 

  11. Fridrich J (2009) Steganography in digital media: principles, algorithms, and applications. Cambridge University Press

  12. Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensic Secur 7(3):868–882

    Article  Google Scholar 

  13. Fridrich J, Kodovskỳ J, Holub V, Goljan M (2011) Steganalysis of content-adaptive steganography in spatial domain. In: Information hiding 13th international conference, IH 2011, Prague, Czech Republic, pp 102–117

  14. Geyer CJ (1992) Practical Markov chain Monte Carlo. Statistical science pp 473–483

  15. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics. pp 249–256

  16. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE international conference on computer vision. pp 1026–1034

  17. Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: 2012 IEEE International workshop on information forensics and security (WIFS). IEEE, pp 234–239

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

    Article  Google Scholar 

  19. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR, pp 448–456

  20. Kaur M, AlZubi AA, Singh D, Kumar V, Lee HN (2023) Lightweight biomedical image encryption approach. IEEE Access 11:74048–74057. https://doi.org/10.1109/ACCESS.2023.3294570

    Article  Google Scholar 

  21. Kaur M, AlZubi AA, Walia TS, Yadav V, Kumar N, Singh D, Lee HN (2023) EGCrypto: a low-complexity elliptic Galois cryptography model for secure data transmission in IoT. IEEE Access 11:90739–90748. https://doi.org/10.1109/ACCESS.2023.3305271

    Article  Google Scholar 

  22. Ker AD, Pevny T (2012) Batch steganography in the real world. In: Proceedings of the on multimedia and security. pp 1–10

  23. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: International conference on learning representations

  24. Kodovsky J, Fridrich J, Holub V (2011) Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensic Secur 7(2):432–444

    Article  Google Scholar 

  25. Larsson G, Maire M, Shakhnarovich G (2016) Fractalnet: ultra-deep neural networks without residuals. In: International conference on learning representations

  26. Li B, He J, Huang J, Shi YQ (2011) A survey on image steganography and steganalysis. J Inf Hiding Multimed Signal Proc 2(2):142–172

    Google Scholar 

  27. Li B, Wang M, Huang J, Li X (2014) A new cost function for spatial image steganography. In: 2014 IEEE International conference on image processing (ICIP). IEEE, pp 4206–4210

  28. Li B, Wang M, Li X, Tan S, Huang J (2015) A strategy of clustering modification directions in spatial image steganography. IEEE Trans Inf Forensic Secur 10(9):1905–1917

    Article  Google Scholar 

  29. Li B, Wei W, Ferreira A, Tan S (2018) ReST-Net: diverse activation modules and parallel subnets-based CNN for spatial image steganalysis. IEEE Signal Proc Lett 25(5):650–654

    Article  ADS  Google Scholar 

  30. Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proc ICML, vol 30, p 3

  31. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems. pp 8026–8037

  32. Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensic Secur 5(2):215–224

    Article  Google Scholar 

  33. Pevny T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. In: Information hiding

  34. Pevnỳ T, Ker AD (2015) Towards dependable steganalysis. In: Media watermarking, security, and forensics 2015, vol 9409, p 94090I. International Society for Optics and Photonics

  35. Provos N, Honeyman P (2003) Hide and seek: an introduction to steganography. IEEE Secur Priv 1(3):32–44

    Article  Google Scholar 

  36. Qian Y, Dong J, Wang W, Tan T (2015) Deep learning for steganalysis via convolutional neural networks. In: Media watermarking, security, and forensics 2015, vol 9409, p 94090J. International Society for Optics and Photonics (2015)

  37. Qian Y, Dong J, Wang W, Tan T (2016) Learning and transferring representations for image steganalysis using convolutional neural network. In: 2016 IEEE international conference on image processing (ICIP). IEEE, pp 2752–2756

  38. Sedighi V, Cogranne R, Fridrich J (2015) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensic Secur 11(2):221–234

    Article  Google Scholar 

  39. Singh B, Chhajed M, Sur A, Mitra P (2020) Steganalysis using learned denoising kernels. Multimed Tool Appl pp 1–15

  40. Singh B, Sharma PK, Saxena R, Sur A, Mitra P (2019) A new steganalysis method using densely connected convnets. In: International conference on pattern recognition and machine intelligence. Springer, pp 277–285

  41. Singh B, Sur A, Mitra P (2021) Steganalysis of digital images using deep fractal network. IEEE Trans Comput Social Syst 8(3):599–606

    Article  Google Scholar 

  42. Song X, Liu F, Yang C, Luo X, Zhang Y (2015) Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: Proceedings of the 3rd ACM workshop on information hiding and multimedia security. pp 15–23

  43. 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. IEEE, pp 1–4

  44. Tang W, Li B, Luo W, Huang J (2015) Clustering steganographic modification directions for color components. IEEE Signal Proc Lett 23(2):197–201

    Article  ADS  Google Scholar 

  45. Wang X, Chen Y, Zhu W (2021) A survey on curriculum learning. IEEE Trans Pattern Anal Mach Intell 44(9):4555–4576

    Google Scholar 

  46. Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Proc Lett 23(5):708–712

    Article  ADS  Google Scholar 

  47. Ye J, Ni J, Yi Y (2017) Deep learning hierarchical representations for image steganalysis. IEEE Trans Inf Forensic Secur 12(11):2545–2557

    Article  Google Scholar 

  48. 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). IEEE, pp 2092–2096

  49. You W, Zhang H, Zhao X (2020) A Siamese CNN for image steganalysis. IEEE Trans Inf Forensic Secur 16:291–306

    Article  Google Scholar 

  50. Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks. In: International conference on machine learning. PMLR, pp 7354–7363

Download references

Funding

This work is supported by the Ministry of Human Resource Development, Govt. of India. We also acknowledge the Department of Biotechnology, Govt. of India for the financial support for the project BT/COE/34/SP28408/2018.

Author information

Authors and Affiliations

  1. Department of CSE, Indian Institute of Technology Guwahati, Guwahati, India

    Brijesh Singh, Arijit Sur & Pinaki Mitra

Authors
  1. Brijesh Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arijit Sur
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pinaki Mitra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Brijesh Singh.

Ethics declarations

Conflicts of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Appendix

Appendix

Fig. 7
figure 7

Comparison among SCA-YeNet, SRNet, and M-CNet in terms of detection error probability \(P_E\) on BOSSBase on (a) WOW, (b) S-Uniward, and (c) HILL steganography

Full size image

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

Singh, B., Sur, A. & Mitra, P. Multi-contextual design of convolutional neural network for steganalysis. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-18545-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11042-024-18545-w

Keywords

Search

Navigation