Constructing feature variation coefficients to evaluate feature learning capabilities of convolutional layers in steganographic detection algorithms of spatial domain

TL;DR

This paper introduces a variation coefficient to quantitatively evaluate the feature learning ability of convolutional layers in CNN-based steganalysis models, and demonstrates its effectiveness in improving detection accuracy.

Contribution

It proposes a novel variation coefficient metric for analyzing convolutional layer effectiveness and uses it to optimize CNN models for steganographic detection.

Findings

Variation coefficient effectively evaluates feature learning ability.

Optimizing features based on the coefficient improves detection accuracy.

Different models show varied improvements after optimization.

Abstract

Traditional steganalysis methods generally include two steps: feature extraction and classification.A variety of steganalysis algorithms based on CNN (Convolutional Neural Network) have appeared in recent years. Among them, the convolutional layer of the CNN model is usually used to extract steganographic features, and the fully connected layer is used for classification. Because the effectiveness of feature extraction seriously influences the accuracy of classification, designers generally improve the accuracy of steganographic detection by improving the convolutional layer. For example, common optimizing methods in convolutional layer include the improvement of convolution kernel, activation functions, pooling functions, network structures, etc. However, due to the complexity and unexplainability of convolutional layers, it is difficult to quantitatively analyze and compare the effectiveness of feature extraction. Therefore, this paper proposes the variation coefficient to evaluate the feature learning ability of convolutional layers. We select four typical image steganalysis models based CNN in spatial domain, such as Ye-Net, Yedroudj-Net, Zhu-Net, and SR-Net as use cases, and verify the validity of the variation coefficient through experiments. Moreover, according to the variation coefficient , a features modification layer is used to optimize the features before the fully connected layer of the CNN model , and the experimental results show that the detection accuracy of the four algorithms were improved differently.