Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 14, pp 19681–19695 | Cite as

A study on Subtractive Pixel Adjacency Matrix features

  • Xiangyuan Gu
  • Jichang GuoEmail author
Article
  • 66 Downloads

Abstract

Subtractive Pixel Adjacency Matrix (SPAM) features perform well in detecting spatial-domain steganographic algorithm. Further, some methods of SPAM features can be applied to rich models and steganalysis based on deep learning. Therefore, this paper presents a study on SPAM features and it is divided into two parts: in the first part, impact of spatial-domain steganographic on difference between adjacent pixels is first analyzed. Then, three SPAM features are proposed with the same range of differences and different orders of Markov chain. Following that, the influences of order of Markov chain and range of differences on SPAM features are analyzed, and we find that detection accuracy of SPAM features increases with the range of differences increasing; in the second part, SPAM feature is first divided into several modules according to the conclusion. Then, taking detection accuracy of support vector machine (SVM) classifier and mutual information as metrics and module as a unit, a Novel Feature Selection (NFS) algorithm and an Improved Feature Selection algorithm are proposed. Experimental results show that the NFS algorithm can achieve higher detection accuracy than several existing algorithms.

Keywords

SPAM features Steganalysis Feature selection Spatial-domain 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (61771334).

References

  1. 1.
    Adeli A, Broumandnia A (2018) Image steganalysis using improved particle swarm optimization based feature selection. Appl Intell 48(6):1609–1622Google Scholar
  2. 2.
    Anita CJ, Ramesh R, Gomathy C, Vaishali D (2018) Nature inspired metaheuristics for improved JPEG steganalysis. Multimed Tools Appl 77 (11):13701–13720Google Scholar
  3. 3.
    ASU feature selection package. http://featureselection.asu.edu
  4. 4.
    Bennasar M, Hicks Y, Setchi R (2015) Feature selection using joint mutual information maximisation. Expert Syst Appl 42(22):8520–8532Google Scholar
  5. 5.
    BOWS2 database. http://bows2.ec-lille.fr
  6. 6.
    Cao WQ, Guan QX, Zhao XF, Wang KR, Han JS (2017) Constructing local information feature for spatial image steganalysis. Multimed Tools Appl 76 (11):13221–13237Google Scholar
  7. 7.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27Google Scholar
  8. 8.
    Cheddad A, Condell J, Curran K, Kevitt PM (2010) Digital image steganography: survey and analysis of current methods. Signal Process 90(3):727–752zbMATHGoogle Scholar
  9. 9.
    Chhikara RR, Sharma P, Singh L (2018) An improved dynamic discrete firefly algorithm for blind image steganalysis. Int J Mach Learn Cybern 9(5):821–835Google Scholar
  10. 10.
    Deng XL, Li YQ, Weng J, Zhang JL (2018) Feature selection for text classification: a review. Multimed Tools Appl, 1–20Google Scholar
  11. 11.
    Estevez PA, Tesmer M, Perez CA, Zurada JM (2009) Normalized mutual information feature selection. IEEE Trans Neural Netw 20(2):189–201Google Scholar
  12. 12.
    Fayyad U, Irani K (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proc. International joint conference on artificial intelligence, pp 1022–1029Google Scholar
  13. 13.
    Feng GR, Zhang HY, Zhang XP (2014) Effective feature selection for image steganalysis using extreme learning machine. J Electron Imag 23(6):063020–1-5Google Scholar
  14. 14.
    Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inform Forens Secur 7(3):868–882Google Scholar
  15. 15.
    Gao WF, Hu L, Zhang P (2018) Class-specific mutual information variation for feature selection. Pattern Recogn 79:328–339Google Scholar
  16. 16.
    Ghareh MF, Saniee AM (2014) Image steganalysis using a bee colony based feature selection algorithm. Eng Appl Artif Intell 31:35–43Google Scholar
  17. 17.
    Holub V, Fridrich J (2013) Random projections of residuals for digital image steganalysis. IEEE Trans Inform Forens Secur 8(12):1996–2006Google Scholar
  18. 18.
    Hosseini HDM, Mahdavi M (2015) F plus KS: a new feature selection strategy for steganalysis. In: Computer science and software engineeringGoogle Scholar
  19. 19.
    Ker AD (2005) Steganalysis of LSB matching in grayscale images. IEEE Signal Process Lett 12(6):441–444Google Scholar
  20. 20.
    Khelifi F, Brahimi T, Han JG, Li XL (2018) Secure and privacy-preserving data sharing in the cloud based on lossless image coding. Signal Process 148:91–101Google Scholar
  21. 21.
    Li B, Li ZP, Zhou SJ, Tan SQ, Xl Zhang (2018) New steganalytic features for spatial image steganography based on derivative filters and threshold LBP operator. IEEE Trans Inform Forens Secur 13(5):1242–1257Google Scholar
  22. 22.
    Liu QZ, Sung AH, Chen ZX (2008) Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images. Pattern Recogn 41(1):56–66zbMATHGoogle Scholar
  23. 23.
    Liu QZ, Sung AH, Ribeiro B, Wei MZ, Chen ZX, Xu JY (2008) Image complexity and feature mining for steganalysis of least significant bit matching steganography. Inform Sci 178(1):21–36Google Scholar
  24. 24.
    Lu JC, Liu FL, Luo XY (2014) Selection of image features for steganalysis based on the Fisher criterion. Digit Investig 11(1):57–66Google Scholar
  25. 25.
    Luo XY, Wang DS, Wang P, Liu FL (2008) A review on blind detection for image steganography. Signal Process 88(9):2138–2157zbMATHGoogle Scholar
  26. 26.
    Miche Y, Roue B, Lendasse A, Bas P (2006) A feature selection methodology for steganalysis. In: Multimedia content representation, classification and security, pp 49–56Google Scholar
  27. 27.
    Mohammadi FG, Abadeh MS (2014) A new metaheuristic feature subset selection approach for image steganalysis. J Intell Fuzzy Syst 27(3):1445–1455Google Scholar
  28. 28.
    Mohammadi FG, Sajedi H (2017) Region based image steganalysis using artificial bee colony. J Vis Commun Image Represent 44:214–226Google Scholar
  29. 29.
    Peng HC, Long FH, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238Google Scholar
  30. 30.
    Pevny T, Bas P, Fridrich J (2009) Steganalysis by Subtractive Pixel Adjacency Matrix. In: ACM Multimedia and security workshop, pp 75–83Google Scholar
  31. 31.
    Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inform Forens Secur 5(2):215–224Google Scholar
  32. 32.
    Sullivan K, Madhow U, Chandrasekaran S, Manjunath BS (2005) Steganalysis of spread spectrum data hiding exploiting cover memory. In: Proc. conference on security, steganography and watermarking of multimedia contents, pp 28–46Google Scholar
  33. 33.
    Wang Y, Moulin P (2007) Optimized feature extraction for learning-based image steganalysis. IEEE Trans Inform Forens Secur 2(1):31–45Google Scholar
  34. 34.
    Wang PF, Wei ZH, Xiao L (2016) Pure spatial rich model features for digital image steganalysis. Multimed Tools Appl 75(5):2897–2912Google Scholar
  35. 35.
  36. 36.
    Wu GS, Lin ZJ, Han JG, Liu L, Ding GG, Zhang BC, Shen JL (2018) Unsupervised deep hashing via binary latent factor models for large-scale cross-modal retrieval. In: Proc. International joint conference on artificial intelligence, pp 2854–2860Google Scholar
  37. 37.
    Xie CH, Cheng YM, Chen YK (2011) An active steganalysis approach for echo hiding based on sliding windowed cepstrum. Signal Process 91(4):877–889zbMATHGoogle Scholar
  38. 38.
    Xu GS, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Process Lett 23(5):708–712Google Scholar
  39. 39.
    Yan CG, Zhang YD, Xu JZ, Dai F, Li L, Dai QH, Wu F (2014) A highly parallel framework for HEVC coding unit partitioning tree decision on many-core processors. IEEE Signal Process Lett 21(5):573–576Google Scholar
  40. 40.
    Yan CG, Xie HT, Chen JJ, Zha ZJ, Hao XH, Zhang YD, Dai QH (2018) A fast uyghur text detector for complex background images. IEEE Trans Multimed 20(12):3389–3398Google Scholar
  41. 41.
    Yan CG, Xie HT, Liu S, Yin J, Zhang YD, Dai QH (2018) Effective uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans Intell Transp Syst 19(1):220–229Google Scholar
  42. 42.
    Yan CG, Xie HT, Yang DB, Yin J, Zhang YD, Dai QH (2018) Supervised hash coding with deep neural network for environment perception of intelligent vehicles. IEEE Trans Intell Transp Syst 19(1):284–295Google Scholar
  43. 43.
    Yao C, Liu YF, Jiang B, Han JG, Han JW (2017) LLE score: a new filter-based unsupervised feature selection method based on nonlinear manifold embedding and its application to image recognition. IEEE Trans Image Process 26(11):5257–5269MathSciNetzbMATHGoogle Scholar
  44. 44.
    Ye J, Ni JQ, Yi Y (2017) Deep learning hierarchical representations for image steganalysis. IEEE Trans Inf Forens Secur 12(11):2545–2557Google Scholar
  45. 45.
    Zeng JS, Tan SQ, Li B, Huang JW (2018) Large-scale JPEG image steganalysis using hybrid deep-learning framework. IEEE Trans Inform Forens Secur 13(5):1200–1214Google Scholar
  46. 46.
    Zou DK, Shi YQ, Su W, Xuan GR (2006) Steganalysis based on Markov model of thresholded prediction-error image. In: Proc. multimedia and expo, pp 1365–1368Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Electrical and Information EngineeringTianjin UniversityTianjinChina

Personalised recommendations