Abstract
In this paper, we propose a light multiscale convolution neural network to detect adaptive MP3 steganography, which can be used in attacking both the MP3 steganography based on Huffman codes substitution and the method through modifying sign bit in MP3 encoding. Especially, we decrease the model size and the occupation of graphics memory based on convolution factorization. At the same time, the convolution kernels with different size are applied in one layer, which is conducive to the retaining of the detection performance. And refer to the residual structure, a shortcut connection is used in the proposed network to enhance the performance of the network. The experimental result shows the accuracy can reach more than 90% when the payload rate is high. And the model size is reduced by 70% than the previous networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, B., Luo, W., Li, H.: Audio steganalysis with convolutional neural network. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec 2017), pp. 85–90. ACM (2017)
Gao, H.: The MP3 steganography algorithm based on Huffman coding. Acta Scientiarum Naturalium Universitatis Sunyatseni 46(4), 32–35 (2007)
Ghasemzadeh, H., Khass, M.T., Arjmandi, M.K.: Audio steganalysis based on reversed psychoacoustic model of human hearing. Digit. Signal Process. 51, 133–141 (2016)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (IJCAI 2010), pp. 249–256 (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), pp. 770–778. IEEE (2016)
Hegemann, R., Leidinger, A., Brito, R.: LAME (1998). https://sourceforge.net/projects/lame/files/lame/
Jin, C., Wang, R., Yan, D.: Steganalysis of MP3Stego with low embedding-rate using Markov feature. Multimed. Tools Appl. 76(5), 6143–6158 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Petitcolas, F.: MP3Stego (1998). http://www.petitcolas.net/steganography/mp3stego/
Ren, Y., Xiong, Q., Wang, L.: A steganalysis scheme for AAC audio based on MDCT difference between intra and inter frame. In: Kraetzer, C., Shi, Y.-Q., Dittmann, J., Kim, H.J. (eds.) IWDW 2017. LNCS, vol. 10431, pp. 217–231. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-64185-0_17
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), pp. 1–9. IEEE (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), pp. 2818–2826. IEEE (2016)
Wang, Y., Yang, K., Yi, X., Zhao, X., Xu, Z.: CNN-based steganalysis of MP3 steganography in the entropy code domain. In: Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec 2018), pp. 55–65. ACM (2018)
Wang, Y., Yi, X., Zhao, X., Su, A.: RHFCN: fully CNN-based steganalysis of MP3 with rich high-pass filtering. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2627–2631. IEEE (2019)
Yan, D., Wang, R., Zhang, L.: A high capacity MP3 steganography based on Huffman coding. J. Sichuan Univ. (Nat. Sci. Ed.) 6, 1281–1286 (2011)
Yang, K., Yi, X., Zhao, X., Zhou, L.: Adaptive MP3 steganography using equal length entropy codes substitution. In: Kraetzer, C., Shi, Y.-Q., Dittmann, J., Kim, H.J. (eds.) IWDW 2017. LNCS, vol. 10431, pp. 202–216. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-64185-0_16
Yang, Y., Wang, Y., Yi, X., Zhao, X., Ma, Y.: Defining joint embedding distortion for adaptive MP3 steganography. In: Proceedings of the 7th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec 2019), pp. 14–24. ACM (2019)
Acknowledgments
This work was supported by NSFC under 61902391, 61972390 and U1736214, and National Key Technology R&D Program under 2016QY15Z2500 and 2019QY0700.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., Yi, X., Zhao, X., Cao, Y. (2020). Light Multiscale Conventional Neural Network for MP3 Steganalysis. In: Wang, H., Zhao, X., Shi, Y., Kim, H., Piva, A. (eds) Digital Forensics and Watermarking. IWDW 2019. Lecture Notes in Computer Science(), vol 12022. Springer, Cham. https://doi.org/10.1007/978-3-030-43575-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-43575-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43574-5
Online ISBN: 978-3-030-43575-2
eBook Packages: Computer ScienceComputer Science (R0)