Abstract
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.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Amirkhani H, Rahmati M (2011) New framework for using image contents in blind steganalysis systems. J Electron Imag 20(1):013016
Cho S, Cha BH, Wang J et al (2013) Block-based image steganalysis: algorithm and performance evaluation. J Vis Commun Image Represent 24(7):846–856
Deng G, Zhao XF, Huang W, Sheng RN (2012) Image texture complexity estimation approach for steganography evaluation. Comput Eng 38(14):116–118
Dhanawe S, Hanchate DB (2014) Tamper detection in database using forensic analysis. Int J Adv Trends Comput Sci Eng 3(6):2319–7242
Dixit A, Dixit R (2017) A review on digital image watermarking techniques. Int J Image Graph Sign Process 9(4):56–66
Filler T, Judas J, Fridrich J (2012) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inform Foren Sec 6(3):920–935
Fridrich J, Filler T (2007) Practical methods for minimizing embedding impact in steganography. Proc SPIE - Int Soc Optic Eng 6505:650502–650502-15
Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inform Foren Sec 7(3):868–882
He K, Zhang X, Ren S, Sun, J (2016) Deep residual learning for image recognition. Proc IEEE Conf Comput Vision Pattern Recogn Las Vegas: 770–778
Holub V, Fridrich J (2013) Digital image steganography using universal distortion. ACM workshop on information hiding and multimedia security (pp.59-68). ACM
Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. IEEE Int Workshop Inform Foren Sec 2(4):234–239
Hu D, Shen Q, Zhou S, Liu X, Fan Y, Wang L (2017) Adaptive steganalysis based on selection region and combined convolutional neural networks. Sec Commun Netw 2017(4):1–9
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. Proc 32nd Int Conf Mach Learn Lille: 448–456
Juarez-Sandoval O, Cedillo-Hernandez M, Nakano-Miyatake M et al. (2016) Image-adaptive steganalysis for LSB matching steganography. Proc 39th Int Conf Telecommun Sign Process, Vienna: 478–483
Liu T, Wang S (2014) A steganalyis scheme based on improved local texture features. Inform Sec Commun Privacy 4:96–102
Liu Q, Sung AH, Chen Z et al (2008) Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images. Pattern Recogn 41(1):56–66
Liu X, Deng R, Choo K K R, et al (2018) Privacy-preserving outsourced calculation toolkit in the cloud. IEEE Trans Depend Secure Comput (99):1–1
Luo X, Song X, Li X et al (2016) Steganalysis of HUGO steganography based on parameter recognition of syndrome-trellis-codes. Multimed Tools Appl 75(21):13557–13583
Ma Y, Luo X, Li X, et al (2018) Selection of rich model Steganalysis features based on decision rough set α-positive region reduction. IEEE Trans Circ Syst Video Technol (99): 1–1
Mao JF (2010) Shangrao: A novel general Steganalysis technique based on cover image describing. Chin J Comput 33(33):569–579
Pevný T, Filler T, Bas P (2010) Using high-dimensional image models to perform highly undetectable steganography. Lect Notes Comput Sci 6387:161–177
Pibre L, Pasquet J, Ienco D, Chaumont M (2016) Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch. Electron Imag 4(8):1–11
Qian Y, Dong J, Wang W, Tan T (2015) Deep learning for steganalysis via convolutional neural networks. SPIE Med Watermark Sec Foren 9409
Sedighi V, Cogranne R, Fridrich J (2015) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inform Foren Sec 11(2):221–234
Sedighi V, Cogranne R, Fridrich J (2016) Content-adaptive steganography by minimizing statistical detectability. IEEE Trans Inf Forensic Sec 1(2):221–234
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S et al (2015) Going deeper with convolutions. Proceedings of the 28th IEEE conference on computer vision and pattern recognition, Boston 1–9
Tang W, Li H, Luo W, Huang J (2014) Adaptive steganalysis against WOW embedding algorithm. Proc 2nd ACM Workshop Inform Hiding Multimed Sec. Salzburg, 91–96
Wang R, Xu MK, Ping XJ, Zhang T (2014) Steganalysis of spatial images based on segmentation. Acta Automat Sin 40(12):2936–2943
Wang R, Xu M, Ping X et al (2015) Steganalysis of JPEG images by block texture based segmentation. Multimed Tools Appl 74(15):5725–5746
Wang LN, Tan XZ, Xu YB, Zhai LM (2017) An adaptive JPEG image steganography based on texture complexity. J Wuhan Univ 63(5):421–426
Wu S, Zhong S, Liu Y (2018) Deep residual learning for image steganalysis. Multimed Tools Appl 77(9):10437–10453
Wu S, Zhong S, Liu Y (2017) Residual convolution network based steganalysis with adaptive content suppression. IEEE International Conference on Multimedia and Expo. pp 241–246
Xu G, Wu HZ, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. IEEE Sign Process Lett 23(5):708–712
Ye J, Ni J, Yi Y (2017) Deep learning hierarchical representations for image Steganalysis. IEEE Trans Inform Foren Sec 12(11):2545–2557
Yuan Y, Lu W, Feng B, Weng J (2017) Steganalysis with CNN using multi-channels filtered residuals. Proc 3rd Int Conf Cloud Comput Sec, Nanjing, 110–120
Zhang Y, Qin C, Zhang W et al (2018) On the fault-tolerant performance for a class of robust image steganography. Signal Process 146:99–111
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhong, S., Jia, C., Chen, K. et al. A novel steganalysis method with deep learning for different texture complexity images. Multimed Tools Appl 78, 8017–8039 (2019). https://doi.org/10.1007/s11042-018-6573-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6573-5