Steganalysis on Internet images via domain adaptive classifier

Abstract

In recent years, various steganalysis algorithms have been proposed and achieved satisfactory performance. However, these conventional methods are not effective for mismatched steganalysis. In real world, there are millions of images captured by different cameras and users transmitted on the Internet every day. The steganalysis on Internet images will encounter steganographic algorithm mismatch (SAM) and cover source mismatch (CSM). Therefore, the steganalysis on the Internet is essentially to solve the mismatch problem. This paper proposes a method to solve the mismatched steganalysis on the Internet images by domain adaptation classifier. It makes the distribution between training and testing sets more similar to obtain better detection performance. We integrate joint distribution adaptation and geometric structure as regularization terms to a standard supervised classifier. Specifically, joint distribution adaptation contains marginal and conditional distributions. And considering the characteristics of steganalysis on the Internet images, we add the conditional regularization in the geometric structure to the existing algorithms. Experimental results (include SAM and CSM) on Internet images show that our method has a better performance than state-of-the-art methods.