Parallelization of Rich Models for Steganalysis of Digital Images using a CUDA-based Approach
Subject Areas : Parallel and Distributed Architectures, Algorithms and SystemsMahmoud Kazemi 1 , Meysam Mirzaee 2 , Reza Isfahani 3
1 - ICT Research Center, University of Imam Hussein, Tehran, Iran
2 - ICT Research Center, University of Imam Hussein, Tehran, Iran
3 - ICT Research Center, University of Imam Hussein, Tehran, Iran
Keywords: Parallelization, CUDA, GPU, Rich models, Steganalysis,
Abstract :
There are several different methods to make an efficient strategy for steganalysis of digital images. A very powerful method in this area is rich model consisting of a large number of diverse sub-models in both spatial and transform domain that should be utilized. However, the extraction of a various types of features from an image is so time consuming in some steps, especially for training phase with a large number of high resolution images that consist of two steps: train and test. Multithread programming is a near solution to decreasing the required time but it’s limited and it ‘snot so scalable too. In this paper, we present a CUDA based approach for data-parallelization and optimization of sub-model extraction process. Also, construction of the rich model is analyzed in detailed, presenting more efficient solution. Further, some optimization techniques are employed to reduce the total number of GPU memory accesses. Compared to single-thread and multi-threaded CPU processing, 10x-12x and 3x-4x speedups are achieved with implementing our CUDA-based parallel program on GT 540M and it can be scaled with several CUDA cards to achieve better speedups.
[1] Moerland, T., “Steganography and Steganalysis”, Leiden Institute of Advanced Computing Science, www.liacs.nl/home/ tmoerl/privtech.pdf.
[2] S. Fazli, M. Moeini, “A robust image watermarking method based on DWT, DCT, and SVD using a new technique for correction of main geometric attacks,” Optik, Vol. 127, No. 2, 2016, PP. 964-972.
[3] H. Farida and S. Lyu, “Steganalysis Using Higher-Order Image Statistics”, IEEE Transactions on information Forensics and Security, February 2006, Vol. 1, PP. 111-119.
[4] Bohme, Rainer. Advanced Statistical Steganalysis. s.l. : Springer, 2009.
[5] Z. Xia, L. Yang, X. Sun, W. Liang, D. Sun and Z. Ruan, “A Learning-Based Steganalytic Method against LSB Matching Steganography”. Changsha, 410082, China : Hunan University, 2011.
[6] J. Fridrich and J. Kodovský, “Quantitative Steganalysis Using Rich Models.”, .USA : Proc. SPIE 8665, Media Watermarking, Security, and Forensics 2013, March 22, 2013.
[7] V. Holub, J. Fridrich, and T. Denemark, “Random Projections of Residuals as an Alternative to Co-occurrences in Steganalysis.”, Department of ECE, SUNY Binghamton, NY, USA : Proc. SPIE 8665, Media Watermarking, Security, and Forensics 2013, March 22, 2013.
[8] Q. Liu, A. H. Sung, “Feature Mining and Neuro-Fuzzy Inference System for Steganalysis of LSB Matching Stegonagraphy in Grayscale Images.” .New Mexico Tech, Socorro, NM 87801, USA : s.n., 2007.
[9] J. Fridrich and J. Kodovský, “Rich Models for Steganalysis of Digital Images”, IEEE Transactions on Information Forensics and Security, vol. 7, no. 3, pp. 868 – 882, June 2012.
[10] T. Pevný, T. Filler, and P. Bas, “Using high-dimensional image models to perform highly undetectable steganography.” In R. Böhme and R. Safavi-Naini, editors, Information Hiding, 12th Interna tiona l Workshop , volume 6387 of Lecture Notes in Computer Science, pp. 161–177, Calgary, Canada, June 28–30, 2010. Springer-Verlag, New York.
[11] W. Luo, F. Huang, and J. Huang, “Edge adaptive image steganography based on LSB matching revisited”, IEEE Transactions on Information Forensics and Security, vol. 5, no. 2, pp. 201–214, June 2010.
[12] NVIDIA Corporation, NVIDIA CUDA C Programming Guide 4.1, 2011.
[13] General Purpose GPU Programming (GPGPU) Web site, http: //www.gpgpu.org, 2010.
[14] J.D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Krger, A.E. Lefohn, and T.J. Purcell, “A Survey of General-Purpose Computation on Graphics Hardware,” Computer Graphics Forum, vol. 26, no. 1, pp. 80-113, Mar. 2007.
[15] I. K. Park, N. Singhal, M. H. Lee, S. CHo, and C. W. Kim, “Design and Performance Evaluation of Image Processing Algorithms on GPUs” IEEE Transactions On Parallel and Distributed Systems, vol. 22, no. 1, pp. 91–104, January 2011.
[16] H. Heidari, A. Chalechale and A. Mohammadabadi, “Parallel implementation of color based image retrieval using CUDA on the GPU”, International Journal of Information Technology and Computer Science (IJITCS), vol. 6, no. 1, December 2013, pp. 33-40.
[17] H. Heidari, A. Chalechale and A.A. Mohammadabadi, “Parallel implementation of texture based image retrieval on The GPU”, International Journal of Image, Graphics and Signal Processing, vol. 5, no. 9, July 2013, pp. 36-42.
[18] A.A. Mohammadabadi, A. Chalechale and H. Heidari, “Parallelized computation for Edge Histogram Descriptor using CUDA on the Graphics Processing Units (GPU)”, 17th CSI International Symposium on Computer Architecture and Digital Systems (CADS 2013), Tehran, 2013, pp. 9-14.
[19] A.A. Mohammadabadi, A. Chalechale and H. Heidari, “GPU implementation of edge histogram descriptor and color moments fused features for efficient image retrieval”, The CSI Journal on Computer Science and Engineering, vol. 9, no. 2, 2013, pp. 22-33.
[20] H. Heidari, A. Chalechale, A.A. Mohammadabadi, “Accelerating of color moments and texture features extraction using GPU based parallel computing”, 8th Iranian Conference on Machine Vision and Image Processing (MVIP), Zanjan, 2013, pp. 430-435.