Speech steganalysis method based on deep residual network

doi:10.11772/j.issn.1001-9081.2020060763

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (3): 774-779.DOI: 10.11772/j.issn.1001-9081.2020060763

Special Issue: 网络空间安全

• Cyber security • Previous Articles Next Articles

Speech steganalysis method based on deep residual network

REN Yiming, WANG Rangding, YAN Diqun, LIN Yuzhen

Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo Zhejiang 315211, China

Received:2020-06-08 Revised:2020-10-14 Online:2021-03-10 Published:2020-12-22
Supported by:
This work is partially supported by the National Natural Science Foundation of China (U1736215, 61672302, 61901237), the Zhejiang Natural Science Foundation (LY20F020010, LY17F020010), the Open Foundation of Key Laboratory of Mobile Network Application Technology of Zhejiang Province (F2018001).

基于深度残差网络的语音隐写分析方法

任奕茗, 王让定, 严迪群, 林昱臻

宁波大学信息科学与工程学院, 浙江宁波 315211

通讯作者: 王让定
作者简介:任奕茗(1994-),男,浙江义乌人,硕士研究生,主要研究方向:多媒体通信、信息安全;王让定(1962-),男,甘肃天水人,教授,博士,CCF会员,主要研究方向:多媒体通信、信息安全、隐写分析;严迪群(1979-),男,浙江余姚人,副教授,博士,CCF会员,主要研究方向:多媒体通信、信息安全;林昱臻(1994-),男,浙江宁波人,硕士研究生,主要研究方向:多媒体通信、信息安全。
基金资助:
国家自然科学基金资助项目（U1736215，61672302，61901237）；浙江省自然科学基金资助项目（LY20F020010，LY17F020010）；浙江省移动网应用技术重点实验室开放基金资助项目（F2018001）。

Abstract

Abstract: Concerning the low detection performance of the Least Significant Bit (LSB) steganography method on WAV-format speech, a speech steganalysis method based on deep residual network was proposed. First, the residual signal of the input speech signal was calculated through a fixed convolutional layer composed of multiple sets of high-pass filters, and a truncated linear unit was adopted to perform truncation to the obtained residual signal. Then, a deep network was constructed by stacking the convolutional layer and the designed residual block to extract the deep feature information of steganography. Finally, the final classification result was output by the classifier composed of the fully connected layer and Softmax layer. Experimental results under the different secret information embedding rates of two steganography methods,Hide4PGP (Hide 4 Pretty Good Privacy) and LSBmatching (Least Significant Bit matching), show that compared with the exising Convolutional Neural Network (CNN)-based steganalysis methods, the proposed method can achieve better performance, and compared with LinNet, the proposed method has the detection accuracy increased by 7 percentage points on detecting Hide4PGP with the embedding rate of 0.1 bps (bit per sample).

Key words: audio, speech, Least Significant Bit (LSB), steganalysis, deep residual network, deep learning

摘要： 针对目前以WAV格式语音为载体的最低有效位（LSB）隐写方法的检测性能较低的问题，提出了一种基于深度残差网络的语音隐写分析方法。首先，通过多组高通滤波器组成的固定卷积层来计算输入语音信号的残差信号，并利用截断线性激活单元对得到的残差信号进行截断操作；然后，通过卷积层与设计的残差块的堆叠来构建深度网络，以提取深层次的隐写特征数据；最后，利用全连接层与Softmax层组成的分类器输出最终的分类结果。实验结果表明，在Hide4PGP和LSBmatching两种隐写方法的不同密信嵌入率下，所提出模型的检测正确率都要优于现有的基于卷积神经网络（CNN）的隐写分析方法。对于0.1 bps嵌入率的Hide4PGP隐写方法，该隐写分析模型的检测正确率比LinNet提高了近7个百分点。

关键词: 音频, 语音, 最低有效位, 隐写分析, 深度残差网络, 深度学习

CLC Number:

TP391

REN Yiming, WANG Rangding, YAN Diqun, LIN Yuzhen. Speech steganalysis method based on deep residual network[J]. Journal of Computer Applications, 2021, 41(3): 774-779.

任奕茗, 王让定, 严迪群, 林昱臻. 基于深度残差网络的语音隐写分析方法[J]. 计算机应用, 2021, 41(3): 774-779.

References

[1] QIAN Y,DONG J,WANG W,et al. Deep learning for steganalysis via convolutional neural networks[C]//Proceedings of the 2015 SPIE-Media Watermarking, Security, and Forensics. Bellingham, WA:SPIE, 2015:No. 94090J.
[2] KRAETZER C,DITTMANN J. Mel-cepstrum based steganalysis for VoIP steganography[C]//Proceedings of the SPIE 6505, Security, Steganography, and Watermarking of Multimedia Contents IX. Bellingham,WA:SPIE,2007:No. 650505.
[3] LIU Q,SUNG A H,QIAO M. Temporal derivative-based spectrum and Mel-cepstrum audio steganalysis[J]. IEEE Transactions on Information Forensics and Security,2009,4(3):359-368.
[4] LIU Q,SUNG A H,QIAO M. Derivative-based audio steganalysis[J]. ACM Transactions on Multimedia Computing, Communications,and Applications,2011,7(3):No. 18.
[5] LUO W,LI H,YAN Q,et al. Improved audio steganalytic feature and its applications in audio forensics[J]. ACM Transactions on Multimedia Computing,Communications,and Applications,2018, 14(2):No. 43.
[6] KODOVSKY J,FRIDRICH J,HOLUB V. Ensemble classifiers for steganalysis of digital media[J]. IEEE Transactions on Information Forensics and Security,2012,7(2):432-444.
[7] PAULIN C,SELOUANI S A,HERVET É. Audio steganalysis using deep belief networks[J]. International Journal of Speech Technology,2016,19(3):585-591.
[8] CHEN B,LUO W,LI H. Audio steganalysis with convolutional neural network[C]//Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security. New York:ACM, 2017:85-90.
[9] LIN Y,WANG R,YAN D,et al. Audio steganalysis with improved convolutional neural network[C]//Proceedings of the 7th ACM Workshop on Information Hiding and Multimedia Security. New York:ACM,2019:210-215.
[10] LIN Z,HUANG Y,WANG J. RNN-SM:fast steganalysis of VoIP streams using recurrent neural network[J]. IEEE Transactions on Information Forensics and Security,2018,13(7):1854-1868.
[11] YANG H,YANG Z,HUANG Y. Steganalysis of VoIP streams with CNN-LSTM network[C]//Proceedings of the 7th ACM Workshop on Information Hiding and Multimedia Security. New York:ACM,2019:204-209.
[12] WANG Y,YANG K,YI X,et al. CNN-based steganalysis of MP3 steganography in the entropy code domain[C]//Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security. New York:ACM,2018:55-65.
[13] REN Y,LIU D,XIONG Q,et al. Spec-ResNet:a general audio steganalysis scheme based on deep residual network of spectrogram[EB/OL].[2020-03-26]. https://arxiv.org/pdf/1901.06838.pdf.
[14] FRIDRICH J,KODOVSKY J. Rich models for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security,2012,7(3):868-882.
[15] YE J,NI J,YI Y. Deep learning hierarchical representations for image steganalysis[J]. IEEE Transactions on Information Forensics and Security,2017,12(11):2545-2557.
[16] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[17] 郭继昌, 何艳红, 魏慧文. 利用模块化残差网络的图像隐写分析[J]. 西安电子科技大学学报,2019,46(1):79-85.(GUO J C,HE Y H,WEI H W. Image steganalysis on the modularized residual network[J]. Journal of Xidian University,2019,46(1):79-85.)
[18] BOROUMAND M, CHEN M, FRIDRICD J. Deep residual network for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security,2019,14(5):1181-1193.
[19] HUANG J,NI J,WAN L,et al. A customized convolutional neural network with low model complexity for JPEG steganalysis[C]//Proceedings of the 7th ACM Workshop on Information Hiding and Multimedia Security. New York:ACM, 2019:198-203.
[20] GAROFOLO J S,LAMEL L F,FISHER W M,et al. TIMIT acoustic continuous speech corpus[EB/OL].[2020-03-26]. https://catalog.ldc.upenn.edu/LDC93S1.
[21] REPP H. Hide4PGP V2.0[EB/OL].[2020-03-10]. http://www.heinz-repp.onlinehome.de/Hide4PGP.htm.
[22] MIELIKAINEN J. LSB matching revisited[J]. IEEE Signal Processing Letters,2006,13(5):285-287.

Speech steganalysis method based on deep residual network

基于深度残差网络的语音隐写分析方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	XU Liyun, YAN Tao, QIAN Yuhua. Audio encryption algorithm in fractional domain based on cascaded chaotic system [J]. Journal of Computer Applications, 2021, 41(9): 2623-2630.
[2]	XIE Defeng, JI Jianmin. Syntax-enhanced semantic parsing with syntax-aware representation [J]. Journal of Computer Applications, 2021, 41(9): 2489-2495.
[3]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[4]	ZHAO Hong, KONG Dongyi. Chinese description of image content based on fusion of image feature attention and adaptive attention [J]. Journal of Computer Applications, 2021, 41(9): 2496-2503.
[5]	XU Jianglang, LI Linyan, WAN Xinjun, HU Fuyuan. Indoor scene recognition method combined with object detection [J]. Journal of Computer Applications, 2021, 41(9): 2720-2725.
[6]	ZHENG Zhiqiang, HU Xin, WENG Zhi, WANG Yuhe, CHENG Xi. Cattle eye image feature extraction method based on improved DenseNet [J]. Journal of Computer Applications, 2021, 41(9): 2780-2784.
[7]	CHEN Chengrui, SUN Ning, HE Shibiao, LIAO Yong. Deep learning-based joint channel estimation and equalization algorithm for C-V2X communications [J]. Journal of Computer Applications, 2021, 41(9): 2687-2693.
[8]	HE Zhenghai, XIAN Yantuan, WANG Meng, YU Zhengtao. Case reading comprehension method combining syntactic guidance and character attention mechanism [J]. Journal of Computer Applications, 2021, 41(8): 2427-2431.
[9]	CAO Yuhong, XU Hai, LIU Sun'ao, WANG Zixiao, LI Hongliang. Review of deep learning-based medical image segmentation [J]. Journal of Computer Applications, 2021, 41(8): 2273-2287.
[10]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[11]	DU Yan, LYU Liangfu, JIAO Yichen. Fuzzy prototype network based on fuzzy reasoning [J]. Journal of Computer Applications, 2021, 41(7): 1885-1890.
[12]	LI Yafang, LIANG Ye, FENG Weiwei, ZU Baokai, KANG Yujian. Deep network embedding method based on community optimization [J]. Journal of Computer Applications, 2021, 41(7): 1956-1963.
[13]	ZHANG Yang, JIANG Minghu. Authorship identification of text based on attention mechanism [J]. Journal of Computer Applications, 2021, 41(7): 1897-1901.
[14]	GAO Qinquan, HUANG Bingcheng, LIU Wenzhe, TONG Tong. Bamboo strip surface defect detection method based on improved CenterNet [J]. Journal of Computer Applications, 2021, 41(7): 1933-1938.
[15]	HOU Xiaohan, JIN Guodong, TAN Lining, XUE Yuanliang. Synthetic aperture radar ship detection method based on self-adaptive and optimal features [J]. Journal of Computer Applications, 2021, 41(7): 2150-2155.