Comparing Classifiers for Universal Steganalysis

Universal Steganalysis rely on extracting higher order statistical features that gets disturbed when hiding the message in a clean image. Due to content adaptive steganographies like HUGO, WOW etc. which embed the data more in textured areas of the image rather than smooth areas by minimizing the distortion of the image itself, first order features are not sufficient to differentiate clean and stego images. Thus, rich models come into picture in which a large number of features are extracted based on higher order noise residuals of clean and stego images. Thus, Universal Steganalyser is essentially a supervised classifier built on high dimensional feature set. To work with such high dimensional features on a large dataset of images is a very challenging task due to curse of dimensionality as well as computationally very expensive. This paper aims at comparing performance of three techniques-Ensemble classifier, Logistic regression and K-Nearest Neighbors on Spatial Rich Model features extracted for benchmarked dataset BOSSbase_1.01, for the better discrimination of clean and stego images.