LAUSR

Steganalysis is a technology of detecting the presence of secret messages in digital media. Recently, many algorithms have been proposed and achieved satisfactory detection accuracy. However, the performance of these algorithms will be reduced by double-compression, due to the mismatch between training and testing sets. To address this problem, we proposed Transferring Feature on Double-compressed JPEG images (TFD) to improve the detection accuracy. Specifically, our algorithm consists of two parts. First, we detect the double-compression of testing images by constructing multi-classifier with Markov feature. Then we transfer the steganalysis feature into a new feature space, in order to reduce the difference of feature distributions between training and testing sets. We intend to obtain a transformation matrix by adjusting the expectation and standard deviation of training set, minimizing the feature discrepancy between both sets and keeping classification ability of training set, simultaneously. The experimental results show that the proposed algorithm has better performance in double-compressed mismatched steganalysis.