An improved entropy-based approach to steganalysis of compressed speech

  • ChuanPeng Guo
  • Wei YangEmail author
  • Liusheng Huang


Compared with more and more steganography techniques motivated by abundant compressed speech, steganalysis is still a challenging task. Many existing studies are based on a single dimensional feature model and it is difficult to have a wide range of applicability. In this paper, a hybrid Markov model is proposed, which is based on the correlation of fixed codebook parameters in speech codec between pulses in a given track. And then, two detecting methods based on entropy are given. One is designed as a single-pulse position based entropy detection method (SPBE). The other is pulse-position pairs based entropy detection method (PPBE). Simultaneously, to solve the problem of inaccurate calculation of the entropy rate of finite length samples, corrected conditional entropy (CCE) is used as an estimate of the Markov chain entropy rate. Experiments show that CCE and entropy are highly complementary, and both can be employed as classification features to achieve better steganalysis results. Finally, the performance of the proposed detection methods is evaluated and compared with the existing detection methods. Results prove that the two methods proposed in this paper are suitable for online and real-time steganographic detection, especially for small-size samples.


Steganalysis Entropy Compressed speech Markov chain 



This work was supported by the National Natural Science Foundation of China (No. 61572456), and the Natural Science Foundation of Jiangsu Province of China (No. BK20151241).


  1. 1.
    (2012) The cmu audio databases. Available at:
  2. 2.
    (2013) Cool edit pro 2.1. Available at:
  3. 3.
    (2017) Speech codec speech processing functions; adaptive multi-rate - wideband (amr-wb) speech codec; transcoding functions. Available at:
  4. 4.
    (2018) Amr speech encoder and decoder. Available at:
  5. 5.
    Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27Google Scholar
  6. 6.
    Cover TM, Thomas JA (2012) Elements of information theory. Wiley, New YorkzbMATHGoogle Scholar
  7. 7.
    Ding Q, Ping X (2010) Steganalysis of compressed speech based on histogram features. In: 6th international conference on wireless communications networking and mobile computing (WiCOM). IEEE, pp 1–4Google Scholar
  8. 8.
    Dittmann J, Hesse D, Hillert R (2005) Steganography and steganalysis in voice-over ip scenarios: operational aspects and first experiences with a new steganalysis tool set. In: International society for optics and photonics, security, steganography, and watermarking of multimedia contents VII, vol 5681, pp 607–619Google Scholar
  9. 9.
    Dumitrescu S, Wu X, Wang Z (2002) Detection of lsb steganography via sample pair analysis, pp 355–372Google Scholar
  10. 10.
    Fridrich J, Goljan M, Du R (2001) Detecting lsb steganography in color, and gray-scale images. IEEE multimedia 8(4):22–28CrossRefGoogle Scholar
  11. 11.
    Geiser B, Vary P (2007) Backwards compatible wideband telephony in mobile networks: Celp watermarking and bandwidth extension 4:IV–533Google Scholar
  12. 12.
    Geiser B, Vary P (2008) High rate data hiding in acelp speech codecs, pp 4005–4008Google Scholar
  13. 13.
    Gianvecchio S, Wang H (2011) An entropy-based approach to detecting covert timing channels. IEEE Transactions on Dependable and Secure Computing 8(6):785–797CrossRefGoogle Scholar
  14. 14.
    Huang Y, Tang S, Zhang Y (2011) Detection of covert voice-over internet protocol communications using sliding window-based steganalysis. IET communications 5(7):929–936CrossRefGoogle Scholar
  15. 15.
    Huang Y, Tao H, Xiao B, Chang C (2017) Steganography in low bit-rate speech streams based on quantization index modulation controlled by keys. Sci China Technol Sci 60(10):1585–1596CrossRefGoogle Scholar
  16. 16.
    Jagtap S, Mulye M, Uplane M (2015) Speech coding techniques. Procedia Computer Science 49:253–263CrossRefGoogle Scholar
  17. 17.
    Kraetzer C, Dittmann J (2007) Mel-cepstrum-based steganalysis for voip steganography 6505:650505Google Scholar
  18. 18.
    Kratzer C, Dittmann J, Vogel T, Hillert R (2006) Design and evaluation of steganography for voice-over-ip. In: IEEE international symposium on circuits and systems, 2006. ISCAS 2006. Proceedings. IEEE, pp 4–ppGoogle Scholar
  19. 19.
    Li S, Huang Y, Lu J (2013) Detection of qim steganography in low bit-rate speech codec based on statistical models and svm. Chin J Comput 36(6):1168–1176MathSciNetCrossRefGoogle Scholar
  20. 20.
    Li S, Jia Y, Kuo CCJ (2017) Steganalysis of qim steganography in low-bit-rate speech signals. IEEE/ACM Transactions on Audio, Speech, and Language Processing 25(5):1011–1022CrossRefGoogle Scholar
  21. 21.
    Liu J, Tian H, Lu J, Chen Y (2016) Neighbor-index-division steganography based on qim method for g. 723.1 speech streams. J Ambient Intell Humaniz Comput 7(1):139–147CrossRefGoogle Scholar
  22. 22.
    Liu L, Li M, Li Q, Liang Y (2008) Perceptually transparent information hiding in g. 729 bitstream, pp 406–409Google Scholar
  23. 23.
    Liu P, Li S, Wang H (2017) Steganography integrated into linear predictive coding for low bit-rate speech codec. Multimedia Tools and Applications 76(2):2837–2859CrossRefGoogle Scholar
  24. 24.
    Lu ZM, Yan B, Sun SH (2005) Watermarking combined with celp speech coding for authentication. IEICE Trans Inf Syst 88(2):330–334CrossRefGoogle Scholar
  25. 25.
    Mazurczyk W (2013) Voip steganography and its detection—a survey. ACM Comput Surv 46(2):20CrossRefGoogle Scholar
  26. 26.
    Miao H, Huang L, Chen Z, Yang W, Al-Hawbani A (2012) A new scheme for covert communication via 3g encoded speech. Comput Electr Eng 38(6):1490–1501CrossRefGoogle Scholar
  27. 27.
    Miao H, Huang L, Shen Y, Lu X, Chen Z (2013) Steganalysis of compressed speech based on markov and entropy. In: International workshop on digital watermarking. Springer, pp 63–76Google Scholar
  28. 28.
    Petitcolas FA, Anderson RJ, Kuhn MG (1999) Information hiding-a survey. Proc IEEE 87(7):1062–1078CrossRefGoogle Scholar
  29. 29.
    Ren Y, Cai T, Tang M, Wang L (2015) Amr steganalysis based on the probability of same pulse position. IEEE Trans Inf Forensic Secur 10(9):1801–1811CrossRefGoogle Scholar
  30. 30.
    Takahashi T, Lee W (2007) An assessment of voip covert channel threats. In: 3rd international conference on security and privacy in communications networks and the workshops. SecureComm 2007. IEEE, pp 371–380Google Scholar
  31. 31.
    Tian H, Qin J, Huang Y, Chen Y, Wang T, Liu J, Cai Y (2015) Optimal matrix embedding for voice-over-ip steganography. Signal Process 117:33–43CrossRefGoogle Scholar
  32. 32.
    Tian H, Wu Y, Chang CC, Huang Y, Chen Y, Wang T, Cai Y, Liu J (2017) Steganalysis of adaptive multi-rate speech using statistical characteristics of pulse pairs. Signal Process 134:9–22CrossRefGoogle Scholar
  33. 33.
    Westfeld A, Pfitzmann A (1999) Attacks on steganographic systems. In: International workshop on information hiding. Springer, pp 61–76Google Scholar
  34. 34.
    Wu Z, Cao H, Li D (2015) An approach of steganography in g. 729 bitstream based on matrix coding and interleaving. Chin J Electron 24(1):157–165CrossRefGoogle Scholar
  35. 35.
    Xiao B, Huang Y, Tang S (2008) An approach to information hiding in low bit-rate speech stream. IEEE, pp 1–5Google Scholar
  36. 36.
    Zhanzhan G, Guangming T, Shuo W (2018) A novel voip steganography method based on bayesian network and matrix embedding. Journal of Computer Research and Development 55(4):854–863. CrossRefGoogle Scholar
  37. 37.
    Zhijun W, Yongpeng S (2016) An implementation of speech steganography for ilbc by using fixed codebook. In: 2nd IEEE international conference on computer and communications (ICCC). IEEE, pp 1970–1974Google Scholar
  38. 38.
    Zielinska E, Mazurczyk W, Szczypiorski K (2014) Trends in steganography. Commun ACM 57(3):86–95CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefeiChina

Personalised recommendations