Backpropagation neural networks, steganography, steganalysis, Blum Blum Shub generator.

: In the paper, we present an approach for identifying the stego-key in key-dependent steganographic schemes. The proposed approach is based on backpropagation neural networks and deals with the image histogram modifications associated with weight configurations of adapted neural networks. The image histogram is the type of histogram acting as a graphical representation of the tonal distribution in a digital image. The stego images that are produced by using such data hiding techniques are inherently robust against main geometrical attacks. The essential part of this article aims to verify the proposed approach in an experimental study. Further, contemporary method of application and results are presented in this paper as an example.