Mesh Discriminative Features for 3D Steganalysis

We propose a steganalytic algorithm for triangle meshes, based on the supervised training of a classifier by discriminative feature vectors. After a normalization step, the triangle mesh is calibrated by one step of Laplacian smoothing and then a feature vector is computed, encoding geometric information corresponding to vertices, edges and faces. For a given steganographic or watermarking algorithm, we create a training set containing unmarked meshes and meshes marked by that algorithm, and train a classifier using Quadratic Discriminant Analysis. The performance of the proposed method was evaluated on six well-known watermarking/steganographic schemes with satisfactory accuracy rates.

[1]  Jessica J. Fridrich,et al.  Steganalysis of JPEG Images: Breaking the F5 Algorithm , 2002, Information Hiding.

[2]  Chengyun Yang,et al.  Steganalysis Based on Multiple Features Formed by Statistical Moments of Wavelet Characteristic Functions , 2005, Information Hiding.

[3]  Ryutarou Ohbuchi,et al.  A Frequency‐Domain Approach to Watermarking 3D Shapes , 2002, Comput. Graph. Forum.

[4]  Craig Gotsman,et al.  Spectral compression of mesh geometry , 2000, EuroCG.

[5]  Ying Yang,et al.  Linear Correlations between Spatial and Normal Noise in Triangle Meshes , 2013, IEEE Transactions on Visualization and Computer Graphics.

[6]  Yu-Ming Cheng,et al.  An Efficient Information Hiding Algorithm for Polygon Models , 2005, Comput. Graph. Forum.

[7]  B. Prabhakaran,et al.  Spectral Watermarking for Parameterized Surfaces , 2012, IEEE Transactions on Information Forensics and Security.

[8]  Hany Farid,et al.  Detecting hidden messages using higher-order statistical models , 2002, Proceedings. International Conference on Image Processing.

[9]  Jessica J. Fridrich,et al.  Calibration revisited , 2009, MM&Sec '09.

[10]  Ying Wang,et al.  Optimized Feature Extraction for Learning-Based Image Steganalysis , 2007, IEEE Transactions on Information Forensics and Security.

[11]  Robin Wilson,et al.  Modern Graph Theory , 2013 .

[12]  Brian Everitt,et al.  Principles of Multivariate Analysis , 2001 .

[13]  D. Freedman,et al.  On the histogram as a density estimator:L2 theory , 1981 .

[14]  Chao-Hung Lin,et al.  A High Capacity 3D Steganography Algorithm , 2009, IEEE Transactions on Visualization and Computer Graphics.

[15]  Rémy Prost,et al.  An Oblivious Watermarking for 3-D Polygonal Meshes Using Distribution of Vertex Norms , 2007, IEEE Transactions on Signal Processing.

[16]  Martin Isenburg,et al.  (Guest Editors) , 2022 .

[17]  Chin-Chen Chang,et al.  An improved data hiding approach for polygon meshes , 2009, The Visual Computer.

[18]  Ying Yang,et al.  Polygonal mesh watermarking using Laplacian coordinates , 2010, Comput. Graph. Forum.

[19]  Bruno Lévy,et al.  Spectral Geometry Processing with Manifold Harmonics , 2008, Comput. Graph. Forum.

[20]  Ja-Chen Lin,et al.  Fragile watermarking for authenticating 3-D polygonal meshes , 2005, IEEE Transactions on Multimedia.

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

[22]  B. Prabhakaran,et al.  A robust spectral approach for blind watermarking of manifold surfaces , 2008, MM&Sec '08.

[23]  Atilla Baskurt,et al.  A Comprehensive Survey on Three-Dimensional Mesh Watermarking , 2008, IEEE Transactions on Multimedia.

[24]  Boon-Lock Yeo,et al.  Watermarking 3D Objects for Verification , 1999, IEEE Computer Graphics and Applications.

[25]  Michael G. Strintzis,et al.  Blind Robust 3-D Mesh Watermarking Based on Oblate Spheroidal Harmonics , 2009, IEEE Transactions on Multimedia.

[26]  Benoit M. Macq,et al.  Data hiding on 3-D triangle meshes , 2003, IEEE Trans. Signal Process..

[27]  Thomas A. Funkhouser,et al.  A benchmark for 3D mesh segmentation , 2009, ACM Trans. Graph..

[28]  Andrew D. Ker.  Steganalysis of LSB matching in grayscale images , 2005, IEEE Signal Processing Letters.

[29]  Mauro Barni,et al.  Wavelet-based blind watermarking of 3D models , 2004, MM&Sec '04.

[30]  Adam Finkelstein,et al.  Robust mesh watermarking , 1999, SIGGRAPH.

[31]  David Zhang,et al.  Robust mesh watermarking based on multiresolution processing , 2001, Comput. Graph..

[32]  Adrian G. Bors,et al.  Surface-Preserving Robust Watermarking of 3-D Shapes , 2011, IEEE Transactions on Image Processing.

[33]  Tony DeRose,et al.  Multiresolution analysis for surfaces of arbitrary topological type , 1997, TOGS.

[34]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[35]  B. Prabhakaran,et al.  Dirichlet Harmonic Shape Compression with Feature Preservation for Parameterized Surfaces , 2010, Comput. Graph. Forum.

[36]  Peter Schröder,et al.  Multiresolution signal processing for meshes , 1999, SIGGRAPH.

[37]  Gene H. Golub,et al.  Matrix computations , 1983 .

[38]  Tomás Pevný,et al.  Merging Markov and DCT features for multi-class JPEG steganalysis , 2007, Electronic Imaging.

[39]  Mauro Barni,et al.  Roughness-Adaptive 3-D Watermarking Based on Masking Effect of Surface Roughness , 2010, IEEE Transactions on Information Forensics and Security.

[40]  Yusuke Higuchi.  Combinatorial curvature for planar graphs , 2001, J. Graph Theory.

[41]  Béla Bollobás,et al.  Modern Graph Theory , 2002, Graduate Texts in Mathematics.

[42]  Hugues Hoppe,et al.  Progressive meshes , 1996, SIGGRAPH.

[43]  YangYing,et al.  Mesh Discriminative Features for 3D Steganalysis , 2014 .