Abstract
Today's digital audio coding algorithms use sophisticated models to maximise the encoding rate with minimal audible distortion. As a result of this complexity, different implementations of one encoding standard tend to produce varying output streams for the same uncompressed input data. This article presents a method to distinguish between encoding programs used to compress ISO/MPEG 1 Audio Layer-3 (MP3) files on the basis of statistical features that can be extracted from the compressed streams. The method employs a Bayesian machine learning classifier to determine the most likely encoder from a vector of 10 features. Experimental evidence suggests that the method is reliable enough to decrease the rate of false positives in a stego-detection case. Thus, it can be considered as a generic tool to increase the overall reliability of steganalysis in MP3 files. Moreover, a post-hoc interpretation of the trained classifier's parameters reveals interesting details about the degree of relation between subsets of the 20 encoding programs examined in the study. Further topics, such as implications on the robustness and possible extensions to different file formats are addressed in the discussion.
Similar content being viewed by others
References
Fraunhofer Institut für Integrierte Schaltungen (IIS), http://www.iis.fraunhofer.de
ISO/IEC 13818-3, Information Technology. Generic Coding of Moving Pictures and Associated Audio: Audio. International Standard (1994)
Petitcolas, F.A.P., Anderson, R.J., Kuhn, M.G.: Information hiding–a survey. Proc. IEEE 87(7), 1062–1078 (1999)
Petitcolas, F.A.P.: MP3Stego, http://www.cl.cam.ac.uk/fapp2/steganography/mp3stego/ (2002)
8hz-mp3, 8Hz Productions, http://www.8hz.com/mp3/ (1998)
Westfeld, A.: Detecting low embedding rates. In: Petitcolas, F.A.P. (ed.) Information Hiding. Fifth International Workshop, LNCS 2578, pp. 324–339. Springer-Verlag, Berlin Heidelberg (2003)
UnderMP3Cover (MP3 stego tool), http://sourceforge.net/projects/ump3c (2004)
Stego-Lame, http://sourceforge.net/projects/stego-lame (2002)
Böhme, R., Westfeld, A.: Statistical characterisation of MP3 encoders for steganalysis. In: ACM Multimedia and Security Workshop, Magdeburg, Germany, pp. 25–34 (2004)
Brandenburg, K., Stoll, G.: ISO-MPEG-1 audio: a generic standard for coding of high-quality digital audio. J. Audio Eng. Soc. 42(10), 780–794 (1994)
IEC 958, Digital Audio Interface, International Standard (1990)
Nilsson, M.: ID3v2—The Audience is Informed. http://www.id3.org (1998)
EncSpot—An MP3 Analyzer. http://www.guerillasoft.nstep.com/EncSpot2 (2002)
Fridrich, J.: Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes. In: Fridrich, J. (ed.) Information Hiding. Sixth International Workshop, LNCS 3200, pp. 67–81. Springer-Verlag, Berlin Heidelberg (2004)
Lyu, S., Farid, H.: Detecting hidden messages using higher-order statistics and support vector machines. In: Petitcolas, F.A.P. (ed.) Information Hiding. Fifth International Workshop, LNCS 2578, pp. 340–354. Springer-Verlag, Berlin, Heidelberg (2003)
Özer, H., Avcibaş, î., Sankur, B., Memon, N.D.: Steganalysis of audio based on audio quality metrics. In: Delp, E., Wong, P.W. (eds.) Security and Watermarking of Multimedia Contents V. Proceedings of SPIE 5020, pp. 55–66 (2003)
Lindley, D.V.: Bayesian statistics—a review. Soc. Ind. Appl. Math. (1995)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)
Langley, P., Iba, W., Thompson, K.: An analysis of Bayesian classifiers. In: Proceedings of the 10th Conference on Artificial Intelligence, pp. 223–228. MIT Press (1992)
Moddemeijer, R.: On estimation of entropy and mutual information of continuous distributions. Signal Process. 16(3), 233–246 (1989)
Huffman, D.: A method for the construction of minimum redundancy codes. Proc. IRE 40, 1098–1101 (1962)
Ihaka, R., Gentlemen, R.: R—a language for data analysis and graphics. J. Comput. Graphics Stat. 5(3), 299–314 (1996)
The R Project for Statistical Computing. http://www.r-project.org
Hipp, M.: MPG123—Fast MP3 Player for Linux and UNIX Systems. http://www.mpg123.de (2001)
Independent JPEG Group. http://www.ijg.org
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Böhme, R., Westfeld, A. Feature-based encoder classification of compressed audio streams. Multimedia Systems 11, 108–120 (2005). https://doi.org/10.1007/s00530-005-0195-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-005-0195-2