Audio steganalysis method based on wavelet packet and adaptive predictor

doi:10.7523/j.issn.2095-6134.2010.1.007

Abstract

Abstract:

An audio steganalysis method based on wavelet packet and adaptive predictor is proposed. In this scheme, audio signals are firstly decomposed by the wavelet packet, the wavelet packet coefficients of high frequency are then predicted by the LMS adaptive predictor, statistics of predicted errors are selected as the statistical features, and finally SVM is implemented as a classifier. The experimental results verify that, for the commonly used steganography methods of additive noise, high classification accuracy can be achieved even in the case of low embedding strength or low embedding rate.

Key words: additive noise model, audio steganalysis, wavelet packet decomposition, adaptive predictor, support vector machine

CLC Number:

TP391

WANG Yu-Jie, GUO Li, WANG Cui-Ping, DING Zhi-Guo. Audio steganalysis method based on wavelet packet and adaptive predictor[J]. , 2010, 27(1): 49-54.

References

[1] Huang J G, Mumford D. Statistics of natural images and models //Proc of the IEEE Int’l Conf on Computer Vision and Pattern Recognition’99, Vol I. Ft Collins: IEEE Computer Society, 1999: 1541-1547.

[2] Ozer H, Avcibacs I, Sankur B. Steganalysis of audio based on audio quality metrics
[J].Proc SPIE-IS & T Electronic Imaging, Santa Clara, CA, USA, 2003, 5020: 55-66.

[3] Altun O, Sharma G, et al. Morphological steganalysis of audio signals and the principle of diminishing marginal distortions //IEEE International Conference on Acoustics, Speech, and Signal Processing. Philadelphia, Pennsylvania, USA, 2005: 21-24.

[4] Ru X M,Zhang H J, Huang X. Steganalysis of audio:attacking the steghide //Proceedings of the Fourth International Conference on Machine Learning and Cybernetics.Guangzhou, 2005:3938-3942.

[5] Micah K Johnson, Lyu S, Farid H. Steganalysis of recorded speech
[J]. Proc SPIE, 2005, 5681:664-672.

[6] Harmsen J J,Peariman W A. Steganalysis of additive noise modelable information hiding
[J]. Proceedings of SPIE on Electronic Imaging,Security, Steganography, and Watermarking of Multimedia Contents, 2003, 5022: 21-24.

[7] 杨建国. 小波分析及其工程应用
[M]. 北京:机械工业出版社,2005:63-67.

[8] Simon Haykin. Adaptive filter theory (4th edition)
[M]. N J, USA, Prentice Hall,2001: 565-567.

[9] ISO/IEC 13818-7 Information technology-generic coding of moving pictures and associated audio information-part 7:advanced audio coding(AAC), ISO/IEC JTC1/SC29 WG11, 1997.

[10] Kirovski, Malvar D H. Spread-spectrum watermarking of audio signals
[J]. IEEE Transactions on Signal Processing,2003,51(4): 1020-1033.

[11] Chang C C,Lin C J.LIBSVM:A library for support vector machines: Tai Wan . 2006

[2007] . http://www.csie.ntu.edu.tw/~cjlin/libsvm.

[12] Heinz.Rep. Hide4PGP V2.0 . 2004.http://www.Heinzrepp.onlinehome.de/Hide4PGP.Html.