Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (7): 1967-1973.DOI: 10.11772/j.issn.1001-9081.2017122883

Previous Articles     Next Articles

Steganalysis based on Bayesian network for compressed speech

YANG Jie1,2, LI Songbin1,2, DENG Haojiang1,2   

  1. 1. Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China;
    2. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2017-12-11 Revised:2018-02-09 Online:2018-07-10 Published:2018-07-12
  • Supported by:
    This work is supported by the National Natural Science Foundation of China (U1636113).


杨洁1,2, 李松斌1,2, 邓浩江1,2   

  1. 1. 中国科学院 声学研究所, 北京 100190;
    2. 中国科学院大学 电子电气与通信工程学院, 北京 100049
  • 通讯作者: 李松斌
  • 作者简介:杨洁(1989-),男,重庆人,博士研究生,主要研究方向:信息安全、多媒体信息处理;李松斌(1981-),男,福建漳州人,副研究员,博士,主要研究方向:多媒体信号处理与取证;邓浩江(1971-),男,北京人,研究员,博士,主要研究方向:多媒体信息处理、宽带多媒体通信、模式识别。
  • 基金资助:

Abstract: In the steganography methods for low-bit-rate compressed speech based on Quantization Index Modulation (QIM), Nearest-neighbor Projection Point QIM (NPP-QIM) steganography has high embedding efficiency and security. Focusing on the issue that the accuracy of the existing steganalysis methods against the NPP-QIM steganography is not high, a steganalysis approach based on Bayesian inference was proposed for improving it. Firstly, Codeword Spatiotemporal Transition Network (CSTN) was constructed by using the Vector Quantization (VQ) codewords VQ1, VQ2, VQ3. Secondly, the codeword transition index was introduced to simplify the CSTN to obtain Steganography-Sensitive CSTN (SS-CSTN). Thirdly, Codeword Bayesian Network (CBN) was further constructed based on SS-CSTN. Finally, the network parameters of CBN were learned by utilizing Dirichlet distribution as the prior distribution to implement QIM steganalysis. The experimental results indicate that the detection accuracy of the proposed CBN method against the NPP-QIM steganography is improved by 25 percentage points and 37 percentage points compared with Index Distribution Characteristic (IDC) method and Derivative Mel-Frequency Cepstral Coefficients (DMFCC) method when the embedding strength is 100% and the speech length is 10 s. In the aspect of time performance, the CBN method can detect a 10 s speech segment in real time with about 21 ms.

Key words: compressed speech, steganography, steganalysis, Quantization Index Modulation (QIM), Bayesian network

摘要: 压缩语音量化索引调制(QIM)信息隐藏方法中,最近邻投影点QIM(NPP-QIM)方法具有较高的嵌入效率和隐蔽性。针对现有的隐写分析方法对NPP-QIM方法检测准确率不高的问题,提出了一种基于贝叶斯推理的检测方法以提高检测准确率。首先,利用矢量量化(VQ)码字(VQ1、VQ2、VQ3)构建了码字时空转移网络(CSTN);接着,以码字转移指数对CSTN进行化简得到隐写敏感码字时空转移网络(SS-CSTN);然后,基于SS-CSTN进一步构建了码字贝叶斯网络(CBN);最后,使用Dirichlet分布作为先验分布学习网络参数,实现对QIM信息隐藏的检测。实验结果表明,在嵌入率为100%、时长为10 s时,与索引分布特征(IDC)方法和梅尔频率倒频系数(DMFCC)方法相比,提出CBN方法的检测准确率分别提高了25个百分点和 37个百分点;在时间性能方法,检测一段10 s的语音时间约为21 ms,能够实时检测。

关键词: 压缩语音, 信息隐藏, 信息隐藏检测, 量化索引调制, 贝叶斯网络

CLC Number: