Blind JPEG Steganalysis Based on Correlations of DCT Cofficients in Multi-Directions and Calibrations

This paper presents a universal steganalysis scheme to detect popular JPEG steganography effectively. First, a new kind of transition probability matrix is constructed to describe correlations of the quantized DCT coefficients in the multi-directions. Second, by merging two different calibrations, a 96-dimensional feature vector is extracted, and then the SVM is trained to build the steganalyzer. The results of a series of experiments performed on 4 kinds of typical steganography in different embedding ratios show that the new method outperforms previous methods to make a more reliable blind detection for these typical stegangraphic methods.