# Steganalysis of Inactive Voice-Over-IP Frames Based on Poker Test

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Work

#### 2.1. Improved VAD Algorithm

#### 2.2. Steganography in Inactive Frame

**Step 1:**- Voice activity detection. Speech samples are divided into frames, and each frame is input into the VAD detector, where the inactive frames are marked with a tag.
**Step 2:**- Encoding and embedding secret messages in inactive frames. All frames are encoded without applying silence compression function. If the frame has been marked in Step 1, suitable parameters of the frame will be embedded with secret messages.
**Step 3:**- Encapsulation and send. All the frames are encapsulated in VoIP packets, which are transmitted over the Internet.

## 3. Steganalysis Based on Poker Test

_{i}be the frequency of the i-th type of subsequence of length m, where 1 $\le $ i $\le $ 2

^{m}. The poker test statistic is defined as

^{m}− 1 degrees of freedom. In the proposed steganalysis method, each parameter suitable for steganography in all inactive frames can form a bit sequence. The bit sequence can be considered as consisting of a series of subsequences, which can be expressed as

_{j}is the subsequence of X of length m. Denote P as the set which contains all the 2

^{m}types of subsequences. Then, the frequency of the i-th type of subsequence can be calculated by

_{i}be the i-th bit in X, the probabilities b

_{i}= 1 and b

_{i}= 0 are denoted as p (b

_{i}= 1) and p (b

_{i}= 0), respectively; denote the embedding rate as r, the probabilities for b

_{i}= 1 and b

_{i}= 0 after steganography are p’(b

_{i}= 1) and p’(b

_{i}= 0), which can be expressed as

_{i}will be nearly equal. For example, let m = 2, there are four types of subsequences ({0,0}, {0,1}, {1,0}, {1,1}) and the probability of each subsequence is approximately equal to 0.25. Based on this, the values of F

_{i}satisfy the following equations:

## 4. SVM-Based Steganalysis Method

**Step 1:**- Sample preparation. Collect a great quantity of speech samples encoded by G.723.1 with both encoding modes and embed secret messages with the steganography in Section 2.2 at different embedding rates.
**Step 2:****Step 3:**- Classifier training. Train the SVM classifier with the feature vector built in Step 2.

**Step 1:**- Feature extraction. Extract the proposed features from the samples to be detected.
**Step 2:**- Decision-making. Input the features extracted in Step 1 into the trained SVM classifier to determine whether the samples to be detected contain secret messages according to the classification results.

## 5. Experimental Result and Analysis

#### 5.1. Experiment Setup and Performance Evaluation

_{TP}is the quantity of true positives, namely, the quantity of steganographic samples identified as steganographic samples; N

_{TN}is the quantity of true negatives, namely, the quantity of cover samples identified as cover samples; N

_{FP}is the quantity of false positives, namely, the quantity of cover samples identified as steganographic samples; N

_{FN}is the quantity of false negatives, namely, the quantity of steganographic samples identified as cover samples. False positive rate (FPR) is the probability of false positives in the total number of negatives, which can be expressed as

_{TN}and N

_{FP}is the total number of negatives, that is, the total number of cover samples. False negative rate (FNR) is the probability of false negatives in the total number of positives, which can be expressed as

_{TP}and N

_{FN}is the total number of positives, that is, the total number of steganographic samples.

#### 5.2. Performance and Analysis

## 6. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Naidu, T.R.K.; Kumar, G.P.; Prasad, T.G. Overview of digital audio steganography techniques. Int. J. Emerg. Technol. Eng.
**2016**, 3, 62–66. [Google Scholar] - Joshi, R.; Venugopala, P.S. Improved security in audio steganography using packet forger at the third level. In Proceedings of the 2017 International Conference on Smart Technologies for Smart Nation (SMARTTECHCON), Bangalore, India, 17–19 August 2017; pp. 363–368. [Google Scholar]
- Liu, H.; Liu, J.; Hu, R.; Yan, X.; Wan, S. Adaptive Audio Steganography Scheme Based on Wavelet Packet Energy. In Proceedings of the 2017 IEEE 3rd International Conference on Big Data Security on Cloud (BIGDATASECURITY), IEEE International Conference on High Performance and Smart Computing (HPSC), and IEEE International Conference on Intelligent Data and Security (IDS), Beijing, China, 26–28 May 2017; pp. 26–31. [Google Scholar]
- Hussain, M.; Wahab, A.W.A.; Javed, N.; Jung, K.H. Hybrid Data Hiding Scheme Using Right-Most Digit Replacement and Adaptive Least Significant Bit for Digital Images. Symmetry
**2016**, 8, 41. [Google Scholar] [CrossRef] - Rajendran, S.; Doraipandian, M. Chaotic Map Based Random Image Steganography Using LSB Technique. Int. J. Netw. Secur.
**2017**, 19, 593–598. [Google Scholar] - Kordov, K.; Stoyanov, B. Least Significant Bit Steganography using Hitzl-Zele Chaotic Map. Int. J. Electron. Telecommun.
**2017**, 63, 417–422. [Google Scholar] [CrossRef] [Green Version] - Stoyanov, B.P.; Zhelezov, S.K.; Kordov, K.M. Least significant bit image steganography bit image steganography algorithm based on chaotic rotation equations. Mathematiques
**2016**, 69, 845–850. [Google Scholar] - Aziz, M.; Tayarani-N, M.H.; Afsar, M. A cycling chaos-based cryptic-free algorithm for image steganography. Nonlinear Dyn.
**2015**, 80, 1271–1290. [Google Scholar] [CrossRef] - Almutairi, A. A Comparative Study on Steganography Digital Images: A Case Study of Scalable Vector Graphics (SVG) and Portable Network Graphics (PNG) Images Formats. Int. J. Adv. Comput. Sci. Appl.
**2018**, 9, 170–175. [Google Scholar] [CrossRef] - Mondal, B.; Sinha, N.; Mandal, T. A Secure Image Encryption Algorithm Using LFSR and RC4 Key Stream Generator. In Proceedings of the 3rd International Conference on Advanced Computing, Networking and Informatics, Bhubaneswar, India, 23–25 June 2016; pp. 227–237. [Google Scholar]
- Kar, N.; Mandal, K.; Bhattacharya, B. Improved chaos-based video steganography using DNA alphabets. ICT Express
**2018**, 4, 6–13. [Google Scholar] [CrossRef] - Dasgupta, K.; Mondal, J.K.; Dutta, P. Optimized video steganography using genetic algorithm (GA). Procedia Technol.
**2013**, 10, 131–137. [Google Scholar] [CrossRef] - Kordov, K.; Lachezar, B. Using Circle Map for Audio Encryption Algorithm. Math. Softw. Eng.
**2017**, 2, 183–189. [Google Scholar] - Bashir, Z.; Wątróbski, J.; Rashid, T.; Zafar, S.; Sałabun, W. Chaotic Dynamical State Variables Selection Procedure Based Image Encryption Scheme. Symmetry
**2017**, 9, 312. [Google Scholar] [CrossRef] - Mazurczyk, W. VoIP steganography and its Detection—A survey. ACM Comput. Surv.
**2013**, 46, 20. [Google Scholar] [CrossRef] - Mazurczyk, W.; Szczypiorski, K. Covert Channels in SIP for VoIP Signalling. Commun. Comput. Inf. Sci.
**2008**, 12, 65–72. [Google Scholar] - Forbes, C.R. A New Covert Channel over RTP. Master’s Thesis, Rochester Institute of Technology, New York, NY, USA, 2009. [Google Scholar]
- Geiser, B.; Vary, P. High rate data hiding in ACELP speech codecs. In Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA, 31 March–4 April 2008; pp. 4005–4008. [Google Scholar]
- Miao, H.; Huang, L.; Chen, Z.; Yang, W.; Al-hawbani, A. A new scheme for covert communication via 3G encoded speech. Comput. Electr. Eng.
**2012**, 38, 1490–1501. [Google Scholar] [CrossRef] - Zhijun, W.; Yongpeng, S. An implementation of speech steganography for iLBC by using fixed codebook. In Proceedings of the 2016 2nd IEEE International Conference on Computer and Communications (ICCC), Chengdu, China, 14–17 October 2016; pp. 1970–1974. [Google Scholar]
- Liu, P.; Li, S.; Wang, H. Steganography integrated into linear predictive coding for low bit-rate speech codec. Multimed. Tools Appl.
**2017**, 76, 2837–2859. [Google Scholar] [CrossRef] - Liu, P.; Li, S.; Wang, H. Steganography in vector quantization process of linear predictive coding for low-bit-rate speech codec. Multimed. Syst.
**2017**, 23, 485–497. [Google Scholar] [CrossRef] - Tian, H.; Liu, J.; Li, S. Improving security of quantization-index-modulation steganography in low bit-rate speech streams. Multimed. Syst.
**2014**, 20, 143–154. [Google Scholar] [CrossRef] - Nishimura, A. Data Hiding in Pitch Delay Data of the Adaptive Multi-Rate Narrow-band Speech Codec. In Proceedings of the 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Kyoto, Japan, 12–14 September 2009; pp. 483–486. [Google Scholar]
- Huang, Y.; Liu, C.; Tang, S.; Bai, S. Steganography integration into a low-bit rate speech codec. IEEE Trans. Inf. Forensics Secur.
**2012**, 7, 1865–1875. [Google Scholar] [CrossRef] - Wu, Z.; Yang, W.; Yang, Y. ABS-based speech information hiding approach. Electron. Lett.
**2003**, 39, 1617–1619. [Google Scholar] [CrossRef] - Janicki, A. Pitch-based Steganography for speex voice codec. Secur. Commun. Netw.
**2016**, 9, 2923–2933. [Google Scholar] [CrossRef] - Huang, Y.F.; Tang, S.; Yuan, J. Steganography in inactive frames of VoIP streams encoded by source codec. IEEE Trans. Inf. Forensics Secur.
**2011**, 6, 296–306. [Google Scholar] [CrossRef] - Lin, R.S. High capacity information hiding scheme using VAD algorithm. In Proceedings of the 2016 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), Nantou, Taiwan, 27–29 May 2016; pp. 1–2. [Google Scholar]
- Li, S.; Jia, Y.; Kuo, C.C.J. Steganalysis of QIM Steganography in Low-Bit-Rate Speech Signals. IEEE/ACM Trans. Audio Speech Lang. Process.
**2017**, 25, 1011–1022. [Google Scholar] [CrossRef] - Lin, Z.; Huang, Y.; Wang, J. RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural Network. IEEE Trans. Inf. Forensics Secur.
**2018**, 13, 1854–1868. [Google Scholar] [CrossRef] - Ren, Y.; Yang, J.; Wang, J.; Wang, L. AMR Steganalysis Based on Second-Order Difference of Pitch Delay. IEEE Trans. Inf. Forensics Secur.
**2017**, 12, 1345–1357. [Google Scholar] [CrossRef] - Tian, H.; Wu, Y.; Chang, C.C.; Huang, Y.; Chen, Y.; Wang, T.; Cai, Y.; Liu, J. Steganalysis of adaptive multi-rate speech using statistical characteristics of pulse pairs. Signal Process.
**2017**, 134, 9–22. [Google Scholar] [CrossRef] - Miao, H.; Huang, L.; Shen, Y.; Lu, X.; Chen, Z. Steganalysis of compressed speech based on Markov and entropy. Lect. Notes Comput. Sci.
**2013**, 8389, 63–76. [Google Scholar] - Ren, Y.; Cai, T.; Tang, M.; Wang, L. AMR Steganalysis Based on the Probability of Same Pulse Position. IEEE Trans. Inf. Forensics Secur.
**2015**, 10, 1801–1811. [Google Scholar] - Malik, H.; Subbalakshmi, K.P.; Chandramouli, R. Nonparametric Steganalysis of QIM Steganography Using Approximate Entropy. IEEE Trans. Inf. Forensics Secur.
**2012**, 7, 418–431. [Google Scholar] [CrossRef] [Green Version] - Yang, W.; Tang, S.; Li, M.; Cheng, Y.; Zhou, Z. Steganalysis of Low Embedding Rates LSB Speech Based on Histogram Moments in Frequency Domain. Chin. J. Electron.
**2017**, 26, 1254–1260. [Google Scholar] [CrossRef] - Shannon, C.E. A mathematical theory of communication. Bell Syst. Tech. J.
**1948**, 27, 379–423. [Google Scholar] [CrossRef] - Dual Rate Speech Coder FOR Multimedia Communications Transmitting at 5.3 and 6.3 kbit/s. Available online: https://www.itu.int/net/itu-t/sigdb/speaudio/AudioForm-s.aspx?val=1117231 (accessed on 1 May 2018).
- Menezes, A.J.; Vanstone, S.A.; Oorschot, P.C.V. Handbook of Applied Cryptography, 1st ed.; CRC Press Inc.: Boca Raton, FL, USA, 1996; ISBN 0-8493-8523-7. [Google Scholar]
- Ibrahim, A.; Dragomir, S.S. A Survey on Cauchy–Bunyakovsky–Schwarz Inequality for Power Series. In Analytic Number Theory, Approximation Theory, and Special Function; Springer: New York, NY, USA, 2014; pp. 247–295. [Google Scholar]
- Chang, C.C.; Lin, C.J. LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol.
**2011**, 2, 27. [Google Scholar] [CrossRef] - Garrido, A. Symmetry and Asymmetry Level Measures. Symmetry
**2010**, 2, 707–721. [Google Scholar] [CrossRef] [Green Version]

**Figure 3.**Accuracy (ACC), false positive rate (FPR) and false negative rate (FNR) at various embedding rates. (

**a**) ACC with 5.3 kbit/s mode; (

**b**) FPR with 5.3 kbit/s mode; (

**c**) FNR with 5.3 kbit/s mode; (

**d**) ACC with 6.3 kbit/s mode; (

**e**) FPR with 6.3 kbit/s mode; (

**f**) FNR with 6.3 kbit/s mode.

**Figure 4.**The receiver operating characteristic (ROC) curves at various embedding rates with both encoding modes. (

**a**) ROC at embedding rate of 30%; (

**b**) ROC at embedding rate of 60%; (

**c**) ROC at embedding rate of 100%; (

**A**) the ROC with 5.3 kbit/s mode; (

**a**) ROC at embedding rate of 30%; (

**b**) ROC at embedding rate of 60%; (

**c**) ROC at embedding rate of 100%; (

**B**) the ROC with 6.3 kbit/s mode.

**Table 1.**Bit allocation of G.723.1 codec with 6.3 kbit/s mode [39].

Parameters | Subframe 0 | Subframe 1 | Subframe 2 | Subframe 3 | Subtotal (bits) |
---|---|---|---|---|---|

Adaptive codebook lags (Olp/Aclg) | 7 | 2 | 7 | 2 | 18 |

LPC indices (Lsf) | - | - | - | - | 24 |

Grid index (Grid) | 1 | 1 | 1 | 1 | 4 |

All the gains combined (Mamp) | 12 | 12 | 12 | 12 | 48 |

Pulse positions (Ppos) | 20 | 18 | 20 | 18 | 73 |

Pulse signs (Pamp) | 6 | 5 | 5 | 5 | 22 |

Total | - | - | - | - | 189 |

**Table 2.**Bit allocation of G.723.1 codec with 5.3 kbit/s mode [39].

Parameters | Subframe 0 | Subframe 1 | Subframe 2 | Subframe 3 | Subtotal (bits) |
---|---|---|---|---|---|

Adaptive codebook lags (Olp/Aclg) | 7 | 2 | 7 | 2 | 18 |

LPC indices (Lsf) | - | - | - | - | 24 |

rid index (Grid) | 1 | 1 | 1 | 1 | 4 |

All the gains combined (Mamp) | 12 | 12 | 12 | 12 | 48 |

Pulse positions (Ppos) | 12 | 12 | 12 | 12 | 48 |

Pulse signs (Pamp) | 4 | 4 | 4 | 4 | 16 |

Total | - | - | - | - | 158 |

**Table 3.**Parameters of the inactive frame suitable for embedding secret messages with 6.3 kbit/s mode [28].

Parameter Name | Lsf | Grid | H_Ppos | L_Ppos | Pamp | Total Bits |
---|---|---|---|---|---|---|

Number of bits | 2 | 4 | 13 | 60 | 22 | 101 |

**Table 4.**Parameters of the inactive frame suitable for embedding secret messages with 5.3 kbit/s mode [29].

Parameter Name | Olp | Lsf | Gains | Grid | Pamp | Ppos | Total Bits |
---|---|---|---|---|---|---|---|

Number of bits | 2 | 3 | 8 | 4 | 16 | 48 | 81 |

Parameters | Embedding Rate | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|

0 | 10% | 20% | 30% | 40% | 50% | 60% | 70% | 80% | 90% | 100% | |

Lsf | 93.68 | 93.68 | 94.66 | 79.55 | 67.59 | 56.76 | 43.99 | 17.81 | 5.93 | 18.78 | 12.47 |

Grid | 3.01 | 3.09 | 2.60 | 2.93 | 3.13 | 6.04 | 4.22 | 5.76 | 5.23 | 3.10 | 0.59 |

H_Ppos | 4.12 | 5.23 | 4.28 | 6.55 | 3.18 | 3.00 | 3.31 | 1.30 | 5.23 | 4.71 | 0.39 |

L_Ppos | 7.52 | 8.25 | 6.26 | 6.67 | 5.88 | 4.48 | 2.73 | 7.93 | 2.71 | 2.85 | 3.06 |

Pamp | 201.45 | 203.87 | 182.85 | 161.63 | 119.60 | 131.89 | 84.86 | 74.00 | 30.68 | 4.37 | 2.99 |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Liu, J.; Tian, H.; Chang, C.-C.; Wang, T.; Chen, Y.; Cai, Y.
Steganalysis of Inactive Voice-Over-IP Frames Based on Poker Test. *Symmetry* **2018**, *10*, 336.
https://doi.org/10.3390/sym10080336

**AMA Style**

Liu J, Tian H, Chang C-C, Wang T, Chen Y, Cai Y.
Steganalysis of Inactive Voice-Over-IP Frames Based on Poker Test. *Symmetry*. 2018; 10(8):336.
https://doi.org/10.3390/sym10080336

**Chicago/Turabian Style**

Liu, Jie, Hui Tian, Chin-Chen Chang, Tian Wang, Yonghong Chen, and Yiqiao Cai.
2018. "Steganalysis of Inactive Voice-Over-IP Frames Based on Poker Test" *Symmetry* 10, no. 8: 336.
https://doi.org/10.3390/sym10080336