IEEE Computational Intelligence Magazine - November 2021 - 84

For further study, a CNN-based data hiding scheme can
be developed and combined with the proposed scheme
to form a universal framework of data hiding with
multiple receivers for various deep networks.
noise are also added into P .M The results
of extraction error e on smallNORB
with 2 routing iterations, a batch size of
50,
n 1= and b 03 .= are shown in Fig. 19.
,
Additional data can be extracted correctly
when
z2 0021
In total, for dataset smallz1
00 . 21 and capacity = 300 or
400 bits for Gaussian noise. For uniform
noise, data are extracted correctly when
..
NORB, the proposed scheme is robust to
Gaussian noise that is not stronger than
N (, .)00 022
stronger than (, .)U 00 02 when the
embedding capacity is less than 400 bits.
V. Conclusion
This paper focuses on data hiding for
multiple receivers. A data hiding scheme
that transmits different additional data to
multiple receivers via CapsNets is proposed.
Additional data are carried out in
the process of CapsNets training with
specific data decoding networks. The
parameters of data decoding networks are
generated using the embedding keys possessed
by the receivers. Therefore, it is
unnecessary to store and transmit the
decoders using covert channels. A receiver
can obtain the data using the correct
embedding key but has no knowledge of
other parts of the additional data. Experimental
results show that the operation of
data embedding does not visibly decrease
the performance of CapsNets. The proposed
scheme is customized for CapsNets.
For further study, a CNN-based data
hiding scheme can be developed and
combined with the proposed scheme to
form a universal framework of data hiding
with multiple receivers for various deep
networks. Some parameters of the embedding
function may be different for various
networks, and a universal strategy can be
designed to optimize the parameters.
Acknowledgment
This work was supported in part by Natural
Science Foundation of China under
and uniform noise that is not
Grant 62002214, 62072295, 62072114,
and U1936214, and supported in part by
Natural Science Foundation of Shanghai
under Grant 19ZR1419000.
References
[1] K. He, X. Zhang, S. Ren, and J. Sun, " Deep residual
learning for image recognition, " in Proc. IEEE Conf.
Comput. Vision Pattern Recognit., 2016, pp. 770-778.
[2] C. Liu et al., " Auto-deeplab: Hierarchical neural architecture
search for semantic image segmentation, " in
Proc. IEEE Conf. Comput. Vision Pattern Recognit., 2019,
pp. 82-92.
[3] K. R. Chowdhary, " Natural language processing, " in
Fundamentals of Artificial Intelligence. New York: SpringerVerlag,
2020, pp. 603-649.
[4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, " ImageNet
classification with deep convolutional neural networks, "
in Proc. Adv. Neural Inf. Process. Syst., 2012, pp.
1097-1105.
[5] Y. Yu, X. Si, C. Hu, and J. Zhang, " A review of recurrent
neural networks: LSTM cells and network architectures, "
Neural Comput., vol. 31, no. 7, pp. 1235-1270,
2019. doi: 10.1162/neco_a_01199.
[6] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran,
B. Sengupta, and A. A. Bharath, " Generative adversarial
networks: An overview, " IEEE Signal Process. Mag.,
vol. 35, no. 1, pp. 53-65, 2018.
[7] X. Wu, Q. Chen, J. You, and Y. Xiao, " Unconstrained
offline handwritten word recognition by position embedding
integrated ResNets model, " IEEE Signal Process.
Lett., vol. 26, no. 4, pp. 597-601, 2019. doi: 10.1109/
LSP.2019.2895967.
[8] S. Sabour, N. Frosst, and G. E. Hinton, " Dynamic
routing between capsules, " in Proc. Adv. Neural Inf. Process.
Syst., 2017, pp. 3856-3866.
[9] Z. Wang, X. Zhang, and Z. Yin, " Joint cover-selection
and payload-allocation by steganographic distortion
optimization, " IEEE Signal Process. Lett., vol. 25, no. 10,
pp. 1530-1534, 2018. doi: 10.1109/LSP.2018.2865888.
[10] Y. Uchida, Y. Nagai, S. Sakazawa, and S. Satoh,
" Embedding watermarks into deep neural networks, "
in Proc. 2017 ACM Int. Conf. Multimedia Retrieval, pp.
269-277.
[11] J. Zhang et al., " Protecting intellectual property of
deep neural networks with watermarking, " in Proc. 2018
Asia Conf. Comput. Commun. Security, pp. 159-172.
[12] Y. Adi, C. Baum, M. Cisse, B. Pinkas, and J. Keshet,
" Turning your weakness into a strength: Watermarking
deep neural networks by backdooring, " in Proc. 27th
{USENIX} Security Symp. ({USENIX} Security 18), 2018,
pp. 1615-1631.
[13] E. L. Merrer, P. Perez, and G. Trédan, " Adversarial
frontier stitching for remote neural network watermarking, "
Neural Comput. Appl., vol. 32, no. 13, pp. 9233-
9244, 2020. doi: 10.1007/s00521-019-04434-z.
[14] H. Wu, G. Liu, Y. Yao, and X. Zhang, " Watermarking
neural networks with watermarked images, " IEEE
Trans. Circuits Syst. Video Technol., vol. 31, no. 7, pp.
2591-2601, 2021. doi: 10.1109/TCSVT.2020.3030671.
[15] J. Wang, H. Wu, X. Zhang, and Y. Yao, " Watermarking
in deep neural networks via error back-propagation, "
Electron. Imag., vol. 2020, no. 4, p. 22-1, 2020. doi:
10.2352/ISSN.2470-1173.2020.4.MWSF-022.
[16] Z. Wang, G. Feng, Y. Ren, and X. Zhang, " Multichannel
steganography in digital images for multiple receivers, "
IEEE Multimedia, vol. 28, no. 1, pp. 65-73, 2021.
doi: 10.1109/MMUL.2020.3045173.
[17] G. E. Hinton, A. Krizhevsky, and S. D. Wang,
" Transforming auto-encoders, " in Proc. Int. Conf. Artif.
Neural Netw., Springer-Verlag, 2011, pp. 44-51.
[18] Y. LeCun, " The MNIST database of handwritten
digits, " 1998. http://yann.lecun.com/exdb/mnist
[19] A. Ahmed, A. Jalal, and K. Kim, " Region and decision
tree-based segmentations for multi-objects detection
and classification in outdoor scenes, " in Proc. 2019 IEEE
Int. Conf. Frontiers Inf. Technol. (FIT), pp. 209-2095. doi:
10.1109/FIT47737.2019.00047.
[20] A. Anand and A. K. Singh, " Watermarking techniques
for medical data authentication: A survey, " Multimedia
Tools Appl., 2020, pp. 1-33.
[21] Z. Wang, G. Feng, and X. Zhang, " Repeatable data
hiding: Towards the reusability of digital images, " IEEE
Trans. Circuits Syst. Video Technol., 2021. doi: 10.1109/
TCSVT.2021.3057599.
[22] A. K. Singh, " Data hiding: Current trends, innovation
and potential challenges, " ACM Trans. Multimedia
Comput., Commun., Appl. (TOMM), 2020, vol. 16, no. 3s,
pp. 1-16.
[23] Y. Guo, O. C. Au, R. Wang, L. Fang, and X. Cao,
" Halftone image watermarking by content aware doublesided
embedding error diffusion, " IEEE Trans. Image Process.,
vol. 27, no. 7, pp. 3387-3402, 2018. doi: 10.1109/
TIP.2018.2815181.
[24] M. Amini, M. O. Ahmad, and M. N. S. Swamy,
" A robust multibit multiplicative watermark decoder
using a vector-based hidden Markov model in wavelet
domain, " IEEE Trans. Circuits Syst. Video Technol., vol.
28, no. 2, pp. 402-413, 2018. doi: 10.1109/TCSVT.
2016.2607299.
[25] T. Filler, J. Judas, and J. Fridrich, " Minimizing additive
distortion in steganography using syndrome-trellis
codes, " IEEE Trans. Inf. Forensics Security, vol. 6, no. 3, pp.
920-935, 2011. doi: 10.1109/TIFS.2011.2134094.
[26] J. Yang, D. Ruan, J. Huang, X. Kang, and Y.-Q. Shi,
" An embedding cost learning framework using Gan, "
IEEE Trans. Inf. Forensics Security, vol. 15, pp. 839-851,
2019. doi: 10.1109/TIFS.2019.2922229.
[27] D. Hu, L. Wang, W. Jiang, S. Zheng, and B. Li,
" A novel image steganography method via deep convolutional
generative adversarial networks, " IEEE Access,
vol. 6, pp. 38,303-38,314, 2018. doi: 10.1109/ACCESS.2018.2852771.
[28]
P. Zhang, C. Li, and C. Wang, " Viscode: Embedding
information in visualization images using encoderdecoder
network, " IEEE Trans. Vis. Comput. Graphics,
vol. 27, no. 2, pp. 326-336, 2021. doi: 10.1109/TVCG.
2020.3030343.
[29] S. Li and X. Zhang, " Toward construction-based
data hiding: From secrets to fingerprint images, " IEEE
Trans. Image Process., vol. 28, no. 3, pp. 1482-1497, 2019.
[30] Z.-L. Yang, X.-Q. Guo, Z.-M. Chen, Y.-F. Huang,
and Y.-J. Zhang. " RNN-stega: Linguistic steganography
based on recurrent neural networks, " IEEE Trans. Inf. Forensics
Security, vol. 14, no. 5, pp. 1280-1295, 2019.
[31] J. Fridrich and D. Soukal, " Matrix embedding for large
payloads, " IEEE Trans. Inf. Forensics Security, vol. 1, no. 3,
pp. 390-395, 2006. doi: 10.1109/TIFS.2006.879281.
[32] G. J. Simmons, " The prisoners problem and the subliminal
channel, " in Advance in Cryptology. New York:
Springer-Verlag, 1984, pp. 51-67.
[33] C. Cachin, " An information-theoretic model for
steganography, " in Proc. Int. Workshop Inf. Hiding, Springer-Verlag,
1998, pp. 306-318.
[34] D. P. Kingma and J. Ba, " Adam: A method for stochastic
optimization, " 2014, arXiv:1412.6980.
[35] J. Tao, S. Li, X. Zhang, and Z. Wang, " Towards
robust image steganography, " IEEE Trans. Circuits Syst.
Video Technol., vol. 29, no. 2, pp. 594-600, 2019. doi:
10.1109/TCSVT.2018.2881118.
[36] A. Krizhevsky, I. Sutskever, and G. Hinton, " Imagenet
classification with deep convolutional networks, "
in Proc. Conf. Neural Inf. Process. Syst. (NIPS), 2012, pp.
1097-1105.
[37] Y. LeCun, F. J. Huang, and L. Bottou, " Learning
methods for generic object recognition with invariance
to pose and lighting, " in Proc. 2004 IEEE Comput. Soc.
Conf. Comput. Vision Pattern Recognit., CVPR 2004, vol.
2, p. II-104.
84 IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | NOVEMBER 2021
http://yann.lecun.com/exdb/mnist
IEEE Computational Intelligence Magazine - November 2021

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - November 2021
