Efficient feature learning and multi-size image steganalysis based on CNN

TL;DR

This paper proposes an improved CNN architecture for image steganalysis that enhances feature extraction, handles arbitrary image sizes, and outperforms existing methods in detecting steganographic algorithms.

Contribution

The paper introduces a CNN design with smaller kernels, separable convolutions, and spatial pyramid pooling to improve steganalysis accuracy and flexibility for images of various sizes.

Findings

Significantly outperforms SRM, Ye-Net, Xu-Net, and Yedroudj-Net in detection accuracy.

Effectively detects multiple steganographic algorithms across diverse datasets.

Enhances signal-to-noise ratio and feature representation in steganalysis.

Abstract

For steganalysis, many studies showed that convolutional neural network has better performances than the two-part structure of traditional machine learning methods. However, there are still two problems to be resolved: cutting down signal to noise ratio of the steganalysis feature map and steganalyzing images of arbitrary size. Some algorithms required fixed size images as the input and had low accuracy due to the underutilization of the noise residuals obtained by various types of filters. In this paper, we focus on designing an improved network structure based on CNN to resolve the above problems. First, we use 3x3 kernels instead of the traditional 5x5 kernels and optimize convolution kernels in the preprocessing layer. The smaller convolution kernels are used to reduce the number of parameters and model the features in a small local region. Next, we use separable convolutions to utilize channel correlation of the residuals, compress the image content and increase the signal-to-noise ratio (between the stego signal and the image signal). Then, we use spatial pyramid pooling (SPP) to aggregate the local features, enhance the representation ability of features, and steganalyze arbitrary size image. Finally, data augmentation is adopted to further improve network performance. The experimental results show that the proposed CNN structure is significantly better than other four methods such as SRM, Ye-Net, Xu-Net, and Yedroudj-Net, when it is used to detect two spatial algorithms such as WOW and S-UNIWARAD with a wide variety of datasets and payloads.