A novel steganalysis method with deep learning for different texture complexity images

Most steganalysis methods based on deep learning don’t distinguish the image texture complexity, but rather to mix all images for training. As a result, the differences of image content between images with different texture complexities are larger than the differences caused by steganographic signal, which is unfavourable for extracting the effective stegananalysis features. In order to reduce the influence of image content difference on steganalysis performance, this paper propose a steganalyais framework adopting the method of training model separately on dividing data sets. Firstly, according to the image texture feature, some correlated statistical features of gray level co-occurrence matrix are used as a measure index of texture complexity, and the data set is divided into several subsets of different complexity according to the index. Secondly, for images with different texture complexities, the corresponding steganalysis models are constructed and trained by using Most Effective Region (MER) and Inception ideas, respectively. For an image to be detected, its texture complexity is calculated first and the corresponding model is used for detection. Finally, an ensemble learning method is used to further improve the framework precision. The experimental results show that our proposed steganalysis method outperforms the handcrafted-features-based steganalysis methods and several CNN-based methods in detection accuracy.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Jing Dong,et al.  Deep learning for steganalysis via convolutional neural networks , 2015, Electronic Imaging.

[3]  Yan Liu,et al.  Deep residual learning for image steganalysis , 2018, Multimedia Tools and Applications.

[4]  Jessica J. Fridrich,et al.  Digital image steganography using universal distortion , 2013, IH&MMSec '13.

[5]  Anuja Dixit,et al.  A Review on Digital Image Watermarking Techniques , 2017 .

[6]  Jiangqun Ni,et al.  Deep Learning Hierarchical Representations for Image Steganalysis , 2017, IEEE Transactions on Information Forensics and Security.

[7]  Jessica J. Fridrich,et al.  Minimizing Additive Distortion in Steganography Using Syndrome-Trellis Codes , 2011, IEEE Transactions on Information Forensics and Security.

[8]  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.

[9]  Qingzhong Liu,et al.  Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images , 2008, Pattern Recognit..

[10]  Mao Jia.  A Novel General Steganalysis Technique Based on Cover Image Describing , 2010 .

[11]  Jessica J. Fridrich,et al.  Designing steganographic distortion using directional filters , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).

[12]  Sheng Ren-nong.  Image Texture Complexity Estimation Approach for Steganography Evaluation , 2012 .

[13]  Jiwu Huang,et al.  Adaptive steganalysis against WOW embedding algorithm , 2014, IH&MMSec '14.

[14]  Jia-Fa Mao,et al.  A Novel General Steganalysis Technique Based on Cover Image Describing: A Novel General Steganalysis Technique Based on Cover Image Describing , 2010 .

[15]  Mohammad Rahmati,et al.  New framework for using image contents in blind steganalysis systems , 2011, J. Electronic Imaging.

[16]  Tao Zhang,et al.  Steganalysis of JPEG images by block texture based segmentation , 2014, Multimedia Tools and Applications.

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

[18]  Jessica J. Fridrich,et al.  Rich Models for Steganalysis of Digital Images , 2012, IEEE Transactions on Information Forensics and Security.

[19]  Weiming Zhang,et al.  Steganalysis of HUGO steganography based on parameter recognition of syndrome-trellis-codes , 2016, Multimedia Tools and Applications.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  C.-C. Jay Kuo,et al.  Block-based image steganalysis: Algorithm and performance evaluation , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[22]  Robert H. Deng,et al.  Privacy-Preserving Outsourced Calculation Toolkit in the Cloud , 2020, IEEE Transactions on Dependable and Secure Computing.

[23]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Yun Q. Shi,et al.  Structural Design of Convolutional Neural Networks for Steganalysis , 2016, IEEE Signal Processing Letters.

[25]  Tomás Pevný,et al.  Using High-Dimensional Image Models to Perform Highly Undetectable Steganography , 2010, Information Hiding.

[26]  Yan Liu,et al.  Residual convolution network based steganalysis with adaptive content suppression , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[27]  Marc Chaumont,et al.  Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch , 2015, Media Watermarking, Security, and Forensics.

[28]  Yuqi Fan,et al.  Adaptive Steganalysis Based on Selection Region and Combined Convolutional Neural Networks , 2017, Secur. Commun. Networks.

[29]  Jian Weng,et al.  Steganalysis with CNN Using Multi-channels Filtered Residuals , 2017, ICCCS.

[30]  Jessica J. Fridrich,et al.  Content-Adaptive Steganography by Minimizing Statistical Detectability , 2016, IEEE Transactions on Information Forensics and Security.

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

[32]  Héctor M. Pérez Meana,et al.  Image-adaptive steganalysis for LSB Matching steganography , 2016, 2016 39th International Conference on Telecommunications and Signal Processing (TSP).