A parallel SRM feature extraction algorithm for steganalysis based on GPU architecture

The Spatial Rich Model (SRM) generates powerful steganalysis features, but has high computational complexity since it requires calculating tens of thousands of convolutions with image noise residuals. Practical applications dealing with a massive amount of image transferred through the Internet would suffer a long computing time if using CPU. To accelerate the steganalysis, we present a parallel SRM feature extraction algorithm based on GPU architecture. We exploit parallelism of the algorithm, modify the original SRM extraction algorithm and employ some strategies to avoid the disadvantage of its sequentiality. Some OpenCL optimization technologies are also used to accelerate the extraction process, such as convolution unrolling, combined memory access, split-merge strategy for co-occurrence matrix calculation. The experimental results show that the speed of the proposed parallel extraction algorithm for different size images is 25~55 times faster than the original single thread algorithm. In addition, when using AMD GPU HD 6850, our algorithm runs 2~4.2 times faster than using a Intel Quad-core CPU. This indicates our algorithm makes good use of the GPU cores.

[1]  Xuezeng Pan,et al.  Hardware Based Steganalysis , 2008 .

[2]  Tomás Pevný,et al.  Steganalysis by subtractive pixel adjacency matrix , 2010, IEEE Trans. Inf. Forensics Secur..

[3]  Andreas Westfeld,et al.  F5-A Steganographic Algorithm , 2001, Information Hiding.

[4]  Jessica J. Fridrich,et al.  Reliable detection of LSB steganography in color and grayscale images , 2001, MM&Sec '01.

[5]  Jessica J. Fridrich,et al.  Ensemble Classifiers for Steganalysis of Digital Media , 2012, IEEE Transactions on Information Forensics and Security.

[6]  Jessica J. Fridrich,et al.  Random Projections of Residuals for Digital Image Steganalysis , 2013, IEEE Transactions on Information Forensics and Security.

[7]  Andrew D. Ker.  Implementing the projected spatial rich features on a GPU , 2014, Electronic Imaging.

[8]  C. Lopez-Ongil,et al.  FPGA-based implementation for steganalysis: a JPEG-compatibility algorithm , 2013, Microtechnologies for the New Millennium.

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

[10]  Jessica J. Fridrich,et al.  Steganalysis of Content-Adaptive Steganography in Spatial Domain , 2011, Information Hiding.

[11]  Jessica J. Fridrich,et al.  Steganalysis of JPEG images using rich models , 2012, Other Conferences.

[12]  Miroslav Goljan,et al.  Steganalysis based on JPEG compatibility , 2001, SPIE ITCom.

[13]  Jessica J. Fridrich,et al.  Random projections of residuals as an alternative to co-occurrences in steganalysis , 2013, Electronic Imaging.

[14]  Li Pei,et al.  A Novel Color Based Particle Filter Algorithm for Object Tracking , 2009 .

[15]  Mayank Tiwary,et al.  A faster and intelligent steganography detection using Graphics Processing Unit in cloud , 2014, 2014 International Conference on High Performance Computing and Applications (ICHPCA).

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

[17]  Claudia Feregrino Uribe,et al.  An analysis of computational models for accelerating the subtractive pixel adjacency model computation , 2015, Comput. Electr. Eng..

[18]  Moulay A. Akhloufi,et al.  GPGPU real-time texture analysis framework , 2011, Electronic Imaging.

[19]  Jian Cao,et al.  GPU Accelerated Target Tracking Method , 2011 .