Feature Selection Based Universal Image Steganalysis: A Survey

Steganography is the technique of hiding communication into multimedia objects such as image, video, audio, and text. On the other hand, steganalysis is the art and science of detecting the existence of an embedded message. Steganalysis can be classified into targeted\specific steganalysis and universal\blind steganalysis. Targeted steganalysis is designed for specific steganography techniques. Whereas, in universal steganography techniques are not familiar to the user. Moreover, the convectional universal steganalysis consists of two main phases: the extraction of features as well as classifying images into stego or clean. Images containing hidden messages are called Stego images. Feature selection is the technique used to decrease feature dimensionality. This literature review provides an overview of universal image steganalysis based on feature selection.