Steganalysis of Digital Images Using Deep Fractal Network

Abstract

In the recent literature on steganalysis, it has been observed that a deeper network is, in general, preferred for detecting low tone embedding noise, e.g., SRNet. However, very recently, a deep model, called FractalNet, became popular, which is based on self-similarity and grows deeper and wider by maintaining a balance between depth and width using a recurrent adaptation of a fundamental building block. In this work, the concept of the FractalNet model has been exploited for steganalytic detection, where the embedded image has been used as input. In a practical scenario, it has been observed that steganalytic detection for test images is increasing if the width of the network can be increased with a certain proportion to the depth. The proposed deep network is designed by repeating a basic fractal block in such a way that a balance between the depth and width of the overall network can be maintained. A comprehensive set of experiments reveals that the proposed model outperformed the state-of-the-art results. An ablation study is also included to justify the proposed architecture in favor of its performance.