14 - Deep learning in steganography and steganalysis

Abstract

For almost 10 years, the detection of a hidden message in an image has been mainly carried out by the computation of rich models (RMs), followed by classification using an ensemble classifier (EC). In 2015 the first study using a convolutional neural network (CNN) obtained the first results of steganalysis by deep learning approaching the performances of the two-step approach (EC + RM). During 2015–2018, numerous publications have shown that it is possible to obtain improved performances, notably in spatial steganalysis, JPEG steganalysis, selection-channel-aware steganalysis, and quantitative steganalysis. This chapter deals with deep learning in steganalysis from the point of view of current methods, by presenting different neural networks from the period 2015–2018, evaluated with a methodology specific to the discipline of steganalysis. We do not intend to repeat the basic concepts of machine learning or deep learning. So we will present the structure of a deep neural network in a generic way and present the networks proposed in the existing literature for different scenarios of steganalysis, and finally, we will discuss steganography by deep learning.