Multimedia Tools and Applications

, Volume 55, Issue 3, pp 525–556 | Cite as

Audio steganalysis of spread spectrum information hiding based on statistical moment and distance metric

  • Wei ZengEmail author
  • Ruimin Hu
  • Haojun Ai


Audio information hiding has attracted more attentions recently. Spread spectrum (SS) technique has developed rapidly in this area due to the advantages of good robustness and immunity to noise attack. Accordingly detecting the SS hiding effectively and verifying the presence of the secrete message are important issues. In this paper we present two steganalysis algorithms for SS hiding. Both the two methods are based on machine learning theory and discrete wavelet transform (DWT). In the algorithm I, we introduce Gaussian mixture model (GMM) and generalize Gaussian distribution (GGD) to character the probability distribution of wavelet sub-band. Then the absolute probability distribution function (PDF) moment is extracted as feature vectors. In the algorithm II, we propose distance metric between GMM and GGD of wavelet sub-band to distinguish cover and stego audio. Four distance metrics (Kullback-Leibler Distance, Bhattacharyya Distance, Earth Mover’s Distance, L2 Distance) are calculated as feature vectors. The support vector machine (SVM) classifier is utilized for classification. The experiment results of both two proposed algorithms can achieve better detecting performance. Even when embedding strength gets 0.0005, the correct detection rate can reach up to 90%. Its simplicity and extensibility indicate further application in other audio steganalysis.


Steganography Steganalysis Audio Spread spectrum 



This work reported is supported by the National Science Foundation of China (grant 60832002), Important National Science & Technology Specific Projects (grant 2010ZX03004-003) and self-research program of Wuhan University (grant 6081012). We thank the anonymous reviewers for their insightful comments that help improve the presentation.


  1. 1.
    Abramovich F, Sapatinas T, Silverman BW (1998) Wavelet thresholding via a bayesian approach. J R Stat Soc Ser B 60:725–749MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Altun O, Sharma G, Celik M, Bocko M (2005) Morphological steganalysis of audio signals and the principle of diminishing marginal distortions. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp 21–24Google Scholar
  3. 3.
    Avcibas I (2006) Audio steganalysis with content-independent distortion measures. IEEE Signal Process Lett 13(2):92–95CrossRefGoogle Scholar
  4. 4.
    Avcibas I, Memon N, Sankur B (2003) Steganalysis using image quality metrics. IEEE Trans Image Process 12(2):221–229MathSciNetCrossRefGoogle Scholar
  5. 5.
    Baptiste J, Urruty H, Lemarechal G (2004) Fundamentals of convex analysis. Springer-Verlag, BerlinGoogle Scholar
  6. 6.
    Basseville M, Benveniste A, Chou KC et al (1992) Modeling and estimation of multiresolution stochastic processes. IEEE Trans Inf Theory 28(2):766–784CrossRefGoogle Scholar
  7. 7.
    Bender W, Gruh D, Morimoto N et al (1996) Techniques for data hiding. IBM Syst J 35(3–4):313–336CrossRefGoogle Scholar
  8. 8.
    Chang CC, Lin CJ (2010) LIBSVM: a library for support vector machines., April 2010
  9. 9.
    Chipman G, Kolaczyk E, McCulloch R (1997) Adaptive bayesian wavelet shrinkage. J Am Stat Assoc 92:1413–1421zbMATHCrossRefGoogle Scholar
  10. 10.
    Chou KC, Heck LP (1994) A multiscale stochastic modeling approach to the monitoring of mechanical systems. In: Proceedings of IEEE International Symposium on Time-Frequency, Time-Scale Analysis, pp 25–27Google Scholar
  11. 11.
    Christian K, Dittmann J (2009) The impact of information fusion in steganalysis on the example of audio steganalysis. Proceeding of Media Forensics and Security XI, vol.7524, 725409-725409-12Google Scholar
  12. 12.
    Crouse MS, Nowak RD, Baraniuk RG (1998) Wavelet-based statistical signal processing using hidden Markov models. IEEE Trans Signal Proc 46(4):886–902MathSciNetCrossRefGoogle Scholar
  13. 13.
    Cvejic N (2004) Algorithms for audio watermarking and steganography. Dissertation, University of OULUGoogle Scholar
  14. 14.
    Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics, PhiladelphiazbMATHGoogle Scholar
  15. 15.
    Daudet L, Torresani B (2002) Hybrid representation for audiophonic signal encoding. Signal Process 82(11):1595–1617zbMATHCrossRefGoogle Scholar
  16. 16.
    Farid H (2002) Detecting hidden messages using higher-order statistical models. In: Proceedings of IEEE International Conference on Image Processing, pp 905–908Google Scholar
  17. 17.
    Fridrich J (2004) Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes. In 6th International Workshop on Information Hiding, LNCS, vol. 3200, pp 67–81Google Scholar
  18. 18.
    Goljan M, Fridrich J, Holotyak T (2006) New blind steganalysis and its implications. In Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents VIII, vol.6072, pp 1–13Google Scholar
  19. 19.
    Gordy JD, Bruton LT (2000) Performance evaluation of digital audio watermarking algorithms. In: Proceedings of the 43th IEEE Midwest Symposium on Circuits and Systems, Vol.1, pp 456–459Google Scholar
  20. 20.
    Hamza O, Ismail A, Bulent S et al (2003) Steganalysis of audio based on audio quality metrics. In: Proceedings of SPIE on Security and Watermarking of Multimedia Contents, pp 55–66Google Scholar
  21. 21.
    Harmsen J, Pearlman W (2003) Steganalysis of additive noise modelable information hiding. In Proceedings of the SPIE, Security and Watermarking of Multimedia Contents V, 5020, 131–142Google Scholar
  22. 22.
    He JH, Huang JW (2006) Steganalysis of stochastic modulation steganography. Sci China F 49(3):273–285MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Holotyak T, Fridrich J, Voloshynovskiy S (2005) Blind statistical steganalysis of additive steganography using wavelet higher order statistics. In: Proceedings of the 9th Conference on Communications and Multimedia Security, pp 273–274Google Scholar
  24. 24.
    Johnson M, Lyu S, Farid H (2005) Steganalysis of recorded speech. In Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents VII, vol. 5681, 664–672Google Scholar
  25. 25.
    Kailath T (1967) The divergence and Bhattacharyya distance measures in signal selection. IEEE Trans Commun Technol 15:52–60CrossRefGoogle Scholar
  26. 26.
    Kalpana S, Hamid RS, Alan CB (2005) Detecting spread spectrum watermarks using natural scene statistics. In Proceedings of IEEE International Conference on Image Processing, vol.2, 1106–1109Google Scholar
  27. 27.
    Korzhik VI, Fink LM (1975) Error-correcting codes on channels with random structure. Svyaz, MoscowGoogle Scholar
  28. 28.
    Kraetzer C, Dittmann J (2007) Mel-cepstrum based steganalysis for voip-steganography. In: Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents IX, vol. 6505, 650505.1-650505.12Google Scholar
  29. 29.
    Kraetzer C, Dittmann J (2008) Pros and cons of mel-cepstrum based audio steganalysis using SVM classification. In Lecture Notes in Computer Science, vol. 4567, 359–377Google Scholar
  30. 30.
    Lang A, Dittmann J (2006) Profiles for evaluation: the usage of Audio WET. In SPIE conference at the Security, Steganography, and Watermarking of Multimedia Contents VIII, pp 60721J.1–60721J.13Google Scholar
  31. 31.
    Li JQ, Barron AR (2000) Mixture density estimation. Advances in neural information processing systems. MIT, CambridgeGoogle Scholar
  32. 32.
    Liu Y, Chiang K, Corbett C, Archibald R et al (2008) A novel audio steganalysis based on high-order statistics of a distortion measure with hausdorff distance. 11th Information Security Conference, Lecture Notes in Computer Science, vol.5222, 487–501Google Scholar
  33. 33.
    Liu ZL, Pan XZ, Shi L, Wang JM, Ping LD (2006) Effective steganalysis based on statistical moments of differential characteristic function. In International Conference on Computational Intelligence and Security, vol. 2, 1195–1198Google Scholar
  34. 34.
    Liu QZ, Sung AH, Bernardete M, Ribeiro B (2008) Steganalysis of multiclass JPEG images based on expanded Markov features and polynomial fitting. In: Proceeding of IEEE International Joint Conference Neural Networks, pp 3351–3356Google Scholar
  35. 35.
    Liu Q, Sung A, Qiao M (2008) Detecting information-hiding in WAV audios. In Proceeding of 19th International Conference on Pattern Recognition, pp 1–4Google Scholar
  36. 36.
    Liu Q, Sung A, Qiao M (2009) Temporal derivative-based spectrum and mel-cepstrum audio steganalysis. IEEE Trans Inf Forensics Secur 4(3):359–368CrossRefGoogle Scholar
  37. 37.
    Liu Q, Sung A, Xu J, Ribeiro B (2006) Image complexity and feature extraction for steganalysis of LSB matching steganography. In: Proceedings of the 18th International Conference on Pattern Recognition, vol. 2, pp 267–270Google Scholar
  38. 38.
    Liu SH, Yao HX, Gao W (2004) Steganalysis based on wavelet texture analysis and neural network. In: Proceeding of 5th World Congress on Intelligent Control and Automation, WCICA 2004, pp 4066–4069Google Scholar
  39. 39.
    Lyu SW, Farid H (2006) Steganalysis using high-order image statistics. IEEE Trans Inf Forensics Secur 1(1):111–119CrossRefGoogle Scholar
  40. 40.
    Marron JS, Wand MP (1992) Exact mean integrated square error. Ann Stat 20(2):712–736MathSciNetzbMATHCrossRefGoogle Scholar
  41. 41.
    Qiao M, Sung A, Liu Q (2009) Feature Mining and Intelligent Computing for MP3 Steganalysis. International Joint Conference on Bioinformatics, Systems Biology and Intelligent Computing (IJCBS), pp 627–630Google Scholar
  42. 42.
    Ru X, Zhang Y, Wu F (2006) Audio steganalysis based on negative resonance phenomenon caused by steganographic tools. Journal Zhejiang Univ, SCIENCE A 7(4):577–583zbMATHCrossRefGoogle Scholar
  43. 43.
    Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vision 40(2):99–121zbMATHCrossRefGoogle Scholar
  44. 44.
    Sfikas G, Constantinopoulos C, Likas A, Galatsanos NP (2005) An analytic distance metric for Gaussian mixture models with application in image retrieval. In: Proceedings of 15th International Conference on Artificial Neural Networks, pp 835–840Google Scholar
  45. 45.
    Shi YQ, Chen CH, Chen W (2007) A markov process based approach to effective attacking JPEG steganography. In 8th International Workshop on Information Hiding, pp 249–264Google Scholar
  46. 46.
    Shi YQ, Xuan GR, Yang CY, Gao JJ et al (2005) Effective steganalysis based on statistical moments of wavelet characteristic function. In IEEE International Conference on Information Technology: Coding and Computing, pp 768–773Google Scholar
  47. 47.
    Sullivan K, Madhow U, Chandrasekaran S, Manjunath BS (2005) Steganalysis of spread spectrum data hiding exploiting cover memory. In Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents VII, vol.5681, pp 38–46Google Scholar
  48. 48.
    Sun YF, Liu FL, Liu B, Wang P (2008) Steganalysis based on difference image. 7th International Workshop on Digital Watermarking, IWDW 2008, LNCS 5450, pp 184–198Google Scholar
  49. 49.
    Surajit R (2003) Distance-based model selection with application to the analysis of gene expression data. University of Pennsylvania State, DissertationGoogle Scholar
  50. 50.
    Van Trees HL (1973) Detection, estimation, and modulation theory, Parts I–II. Wiley, ChichesterGoogle Scholar
  51. 51.
    Vlassis N, Likas A (2002) A greedy EM algorithm for Gaussian mixture learning. Neural Process Lett 15(1):77–87zbMATHCrossRefGoogle Scholar
  52. 52.
    Wang Y, Moulin P (2003) Steganalysis of block-DCT image steganography. In: IEEE workshop on Statistical Signal Process, pp 339–342Google Scholar
  53. 53.
    Wang Y, Moulin P (2008) Perfectly secure steganography: capacity, error exponents, and code constructions. IEEE Trans Inf Theory 54(6):2706–2722MathSciNetCrossRefGoogle Scholar
  54. 54.
    Wav surfer database (2010) April 2010
  55. 55.
    Wei QQ, Wang DS (2007) Steganalysis of LSB replacement based on wavelet transform. Journal of Tsinghua University (Sci&Tech) 47(4):595–598zbMATHGoogle Scholar
  56. 56.
    Xuan G, Shi Y, Gao J et al (2005) Steganalysis based on multiple features formed by statistical moments of wavelet characteristic functions. In: Proceeding of Information Hiding Workshop, pp 262–277Google Scholar
  57. 57.
    Zhai WD, Lv SW, Liu ZH (2004) Spatial stego-detecting algorithm in color images based on GGD. J China Inst Commun 25(2):33–42Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhanChina

Personalised recommendations