An end-to-end generative network for environmental sound-based covert communication

Environmental sounds, everyday audio events that do not consist of music or speech data and are often more diverse and chaotic in their structure, have proven to be a promising type of carrier signals to carry out covert communication as they occur frequently in the natural environment, e.g., marine communication by mimicking dolphin or sea lion whistles. However, a mass collection of the carrier signals still remains a challenging task. Recently proposed generator models represented by Generator Adversarial Nets (GAN) have provided an effective way to synthesize environmental sounds. In this study, an end-to-end convolutional neural network (CNN) is proposed to directly transform the randomly sampled Gaussian noise into environmental sound that contains the secret message. The proposed network structure is composed of upsampling groups and orthogonal quantization layer, which can simultaneously realize factor analysis and information embedding. The design of the orthogonal quantization layer to complete the message embedding task is inspired by spread spectrum, model-based modulation, and compensative quantization. The underlying idea in this study is to treat the secret message as the constraint information in the generative model with the aim of maximizing the complete data model. The alternating back-propagation algorithm is used to train the overall network. Experimental results show that the proposed scheme can generate realistic environmental sounds that convey secret messages, while guaranteeing a high degree of communication reliability.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Bin Li,et al.  CNN-Based Adversarial Embedding for Image Steganography , 2019, IEEE Transactions on Information Forensics and Security.

[3]  Guanshuo Xu,et al.  Deep Convolutional Neural Network to Detect J-UNIWARD , 2017, IH&MMSec.

[4]  Kai Liu,et al.  Spatial Image Steganography Based on Generative Adversarial Network , 2018, ArXiv.

[5]  Jessica J. Fridrich,et al.  Practical methods for minimizing embedding impact in steganography , 2007, Electronic Imaging.

[6]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[7]  Sebastian Zander,et al.  Pattern-Based Survey and Categorization of Network Covert Channel Techniques , 2014, ACM Comput. Surv..

[8]  Lihua Zhang,et al.  Bionic camouflage underwater acoustic communication based on sea lion sounds , 2015, 2015 International Conference on Control, Automation and Information Sciences (ICCAIS).

[9]  Josh H. McDermott,et al.  Distinct Cortical Pathways for Music and Speech Revealed by Hypothesis-Free Voxel Decomposition , 2015, Neuron.

[10]  Fenlin Liu,et al.  Extracting hidden messages of MLSB steganography based on optimal stego subset , 2018, Science China Information Sciences.

[11]  Songzuo Liu,et al.  Biologically inspired covert underwater acoustic communication using high frequency dolphin clicks , 2013, 2013 OCEANS - San Diego.

[12]  Weiming Zhang,et al.  On the fault-tolerant performance for a class of robust image steganography , 2018, Signal Process..

[13]  Goutam Saha,et al.  Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition , 2012, Speech Commun..

[14]  Saikat Guha,et al.  Covert Communication in the Presence of an Uninformed Jammer , 2016, IEEE Transactions on Wireless Communications.

[15]  Xiangyang Luo,et al.  Selection of Rich Model Steganalysis Features Based on Decision Rough Set $\alpha$ -Positive Region Reduction , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  Songzuo Liu,et al.  Covert underwater acoustic communication using whale noise masking on DSSS signal , 2013, 2013 MTS/IEEE OCEANS - Bergen.

[17]  Matthieu R. Bloch,et al.  Covert Communication Over Noisy Channels: A Resolvability Perspective , 2015, IEEE Transactions on Information Theory.

[18]  Craig A. Knoblock,et al.  A Survey of Digital Map Processing Techniques , 2014, ACM Comput. Surv..

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[20]  Feng Shu,et al.  Covert Communication in Wireless Relay Networks , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[21]  Donald F. Towsley,et al.  Covert Communications When the Warden Does Not Know the Background Noise Power , 2016, IEEE Communications Letters.

[22]  Sung Wook Baik,et al.  Mobile-cloud assisted framework for selective encryption of medical images with steganography for resource-constrained devices , 2017, Multimedia Tools and Applications.

[23]  Wojciech Mazurczyk,et al.  Trends in steganography , 2014, Commun. ACM.

[24]  Bin Li,et al.  Automatic Steganographic Distortion Learning Using a Generative Adversarial Network , 2017, IEEE Signal Processing Letters.

[25]  Eero P. Simoncelli,et al.  Sound texture synthesis via filter statistics , 2009, 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[26]  Dorothy T. Thayer,et al.  EM algorithms for ML factor analysis , 1982 .

[27]  Xiangyun Zhou,et al.  On Covert Communication With Noise Uncertainty , 2016, IEEE Communications Letters.

[28]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[29]  Karol J. Piczak.  ESC: Dataset for Environmental Sound Classification , 2015, ACM Multimedia.

[30]  Songzuo Liu,et al.  Covert underwater acoustic communication using dolphin sounds. , 2013, The Journal of the Acoustical Society of America.

[31]  Jeffrey S. Rosenthal,et al.  Optimal Proposal Distributions and Adaptive MCMC , 2011 .

[32]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[33]  Henry Dol,et al.  Covert Underwater Communication with Marine Mammal Sounds , 2008 .

[34]  Jing Dong,et al.  SSGAN: Secure Steganography Based on Generative Adversarial Networks , 2017, PCM.

[35]  Eero P. Simoncelli,et al.  Article Sound Texture Perception via Statistics of the Auditory Periphery: Evidence from Sound Synthesis , 2022 .

[36]  Ehab Al-Shaer,et al.  A Novel Class of Robust Covert Channels Using Out-of-Order Packets , 2017, IEEE Transactions on Dependable and Secure Computing.

[37]  Bin Li,et al.  CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography , 2018, ArXiv.

[38]  Tian Han,et al.  Alternating Back-Propagation for Generator Network , 2016, AAAI.

[39]  Radford M. Neal.  MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.