Security and Privacy in New Computing Environments. Second EAI International Conference, SPNCE 2019, Tianjin, China, April 13–14, 2019, Proceedings

Research Article

Detecting Steganography in AMR Speech Based on Pulse Correlation

Download
87 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-21373-2_39,
        author={Jie Liu and Hui Tian and Xiaokang Liu and Jing Lu},
        title={Detecting Steganography in AMR Speech Based on Pulse Correlation},
        proceedings={Security and Privacy in New Computing Environments. Second EAI International Conference, SPNCE 2019, Tianjin, China, April 13--14, 2019, Proceedings},
        proceedings_a={SPNCE},
        year={2019},
        month={6},
        keywords={Steganography Steganalysis Adaptive multi-rate speech Pulse correlation Self-information Mutual-information},
        doi={10.1007/978-3-030-21373-2_39}
    }
    
  • Jie Liu
    Hui Tian
    Xiaokang Liu
    Jing Lu
    Year: 2019
    Detecting Steganography in AMR Speech Based on Pulse Correlation
    SPNCE
    Springer
    DOI: 10.1007/978-3-030-21373-2_39
Jie Liu1,*, Hui Tian1,*, Xiaokang Liu1,*, Jing Lu1,*
  • 1: National Huaqiao University
*Contact email: liujiecs@hqu.edu.cn, htian@hqu.edu.cn, xkliu@hqu.edu.cn, jlu@hqu.edu.cn

Abstract

This paper presents a novel methodology to detect the steganography on the fixed codebook (FCB) of adaptive multi-rate (AMR) speech stream. We have found that correlations of pulses are influenced by the steganographic operation. Based on this, two categories of features are proposed to characterize the pulse correlations, namely subframe-level pulse correlation based on self-information and track-level pulse correlation based on mutual-information, whose feature dimension is only 1/5 of the state of the art. The proposed method employs the support vector machine as the classifier and is evaluated with a large quantity of AMR speech samples. The experimental results demonstrate that the propose method is effective and has a better detection performance than the state of the arts.