Steganalysis for Reversible Data Hiding based on Neural Networks and Convolutional Neural Networks

Ho Thi Huong Thom; Kim Anh Nguyen; Bui Dinh Vu

Authors

Ho Thi Huong Thom Faculty of Information Technology, Vietnam Maritime University, Vietnam https://orcid.org/0000-0002-1825-9577
Kim Anh Nguyen, Nguyen Kim Anh Vietnam maritime university https://orcid.org/0000-0003-0885-6850
Bui Dinh Vu, Bui Dinh Vu Vietnam maritime university https://orcid.org/0000-0002-2914-9613

Keywords:

Steganography, Steganalysis, Histogram Shifting, Lossless Data Hiding, Stego Image, Convolutional Neural Networks, Neural Networks

Abstract

Lossless data hiding techniques is a technique that is very interested. In which there is a large amount of reversible information hidden technologies. This technique is technically possible to restore the original image after extracting the information from the stego image. The stego image (image to be hidden secret data) is not detected hardly any variable. There are many studies for this field is published. Secret information is hidden on the pixel space, frequency (cosine, wavelet) coefficient space or difference image coefficient space. However, by analysing meticulously between the cover image and the stego image on these space can be detect abnormal signs. In my previous work, we produced a steganalytic techniques based on analysing the transform coefficient histogram with the correct detection ratio between 88% and 92%. In this article, my team give another method to improve the detection ratio of that steganalysis based on Neural Networks (NNs) and Convolutional Neural Networks (CNNs). Our test results show 94% correct detection rates for NNs and 93% for CNNs, this is a better result than our previous method. This proposed approach can be applied to detect stego images on spatial and other frequency domain.

Author Biographies

Ho Thi Huong Thom, Faculty of Information Technology, Vietnam Maritime University, Vietnam

Ho Thi Huong Thom received the B.S. degree of Information Technology department from Haiphong Private University, the M.S. degree and PhD degree in Information Systems from College of Technology, Vietnam National University in Vietnam, in 2001, 2005 and 2012, respectively. She started her career as Lecturer in Department of Information Technology in Haiphong Private University, Vietnam and served 12 years. From 2014, She has been teaching at Vietnam maritime university (VMU). Her area of interest is information security.

Kim Anh Nguyen, Nguyen Kim Anh, Vietnam maritime university

Nguyen Kim Anh obtained her master's degree in 2009 in Computer Science and Engineering from Centre for Development of Advanced Computing, Noida, India and her bachelor's degree in 2005 in Information Technology form Vietnam Maritime University. She is currently working as a lecture in Information Technology Department in Vietnam Maritime University. Her area of interest is information security and information system.

Bui Dinh Vu, Bui Dinh Vu, Vietnam maritime university

Bui Dinh Vu obtained a bachelor's degree in Information Technology from Hanoi National University in 1998. He obtained his master’s degree in Computer Science from Hanoi Military Technical Academy in 2006. He currently working at the Faculty of Information Technology, Vietnam Maritime University. His area of interest is information security and information system.

References

O. Egger, M. Kunt, Embedded zerotree based lossless image coding, Proceedings., International Conferenceon Image Processing, Washington,DC,USA,USA (2015), https://doi.org/10.1109/icip.1995.537710

. Ni, Z., Shi, Y., Ansari, N., Su, W.: Reversible data hiding. Proc. ISCAS (2003) 912–915. https://doi.org/10.1109/iscas.2003.1206123.

. Sang-Kwang Lee, Young-Ho Suh, and Yo-Sung Ho, Lossless Data Hiding Based on Histogram Modification of Difference Images, PCM 2004, LNCS 3333 (2004) 340–347. https://doi.org/10.1007/978-3-540-30543-9_43

. Xuan, G., Zhu, J., Chen, J., Shi, Y., Ni, Z., Su, W.: Distortionless data hiding based on integer wavelet transform. IEEEElectrionics Letters (2002) 1646–1648.https://doi.org/10.1049/el:20021131

. Guorong Xuan, Qiuming Yao, ChengyunYang, Jianjiong Gao, Peiqi Chai, Yun Q. Shi, Zhicheng Ni, Lossless Data Hidding Using Histogram Shifting Method Based on Integer Wavelets,Proc. 5th Digital watermarking workshop, IWDW 2006, Korea, vol. 4283, pp. 323-332.https://doi.org/10.1007/11922841_26

. Ho Thi Huong Thom, Ho Van Canh, Trinh Nhat Tien, Steganalysis to Reversible Data Hiding, Proceedings of FGIT 2009 (the Future Generation Information Technology Conference) on Database Theory and Application, Springer-Verlag, Jeju Island, Korea (2009), pp. 1- 6.https://doi.org/10.1007/978-3-642-10583-8_1

. F.-J. Huang and Y. LeCun, Large-scale learning with svmand convolutional nets for generic object categorization, in Proc. Computer Vision and Pattern Recognition Conference(CVPR’06). IEEE Press, 2006. https://doi.org/10.1109/cvpr.2006.164

. D. C. Ciresan, U. Meier, J. Masci, and J. Schmidhuber, A committee of neural networks for trafﬁc sign classiﬁcation,” in International Joint Conference on Neural Networks, to appear, 2011. https://doi.org/10.1109/ijcnn.2011.6033458

. StamatiosLefkimmiatis, Non-local Color Image Denoising with Convolutional Neural Networks, in IEEE Conference on Computer Vision and Pattern Recognition 2017 (CVPR 2017). https://doi.org/10.1109/cvpr.2017.623

. Y.A. Alotaibi, High performance Arabic digits recognizer using neural networks, in Proceedings of the International Joint Conference on Neural Networks, 2003.https://doi.org/10.1109/ijcnn.2003.1223444

. H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng, Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in Proceedings of the 26th International Conference on Machine Learning, 2009, pp.609–616.https://doi.org/10.1145/1553374.1553453

. M. D. Zeiler, D. Krishnan, G. W. Taylor, and R. Fergus, Deconvolutional Networks, in Proc. Computer Vision and Pattern Recognition Conference (CVPR 2010), 2010.https://doi.org/10.1109/cvpr.2010.5539957

. Hyeonseob Nam, Bohyung Han, Learning Multi-domain Convolutional Neural Networks for Visual Tracking, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2016),https://doi.org/10.1109/cvpr.2016.465

. D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber. Convolutional neural network committees for handwritten character classification. In International Conference on Document Analysis and Recognition (2011), pages 1250–1254.https://doi.org/10.1109/icdar.2011.229

. CBIR image database, University of Washington, available at:http://www.cs.washington.edu/research/imagedatabase/groundtruth/

. USC-SIPI Image Database, http://sipi.usc.edu/services/database/Database.html.