Sensitivity of a Convolutional Neural Network for Different Pooling Layers in Spatial Domain Steganalysis

In the modern era, numerous research studies consistently affirm the superior performance of Convolutional Neural Networks (CNNs) over traditional machine learning methods in steganalysis, a technique used to detect hidden data through steganography. Deep Learning (DL), particularly CNNs, is a powerful tool for steganalysis because it can handle large datasets effectively. Despite CNNs being widely used in various research areas, previous steganalysis studies have primarily focused on improving image classification (cover or stego), often neglecting a thorough exploration of the experimental setup. This research aims to assess the sensitivity of a CNN-based steganalysis model by investigating the impact of different pooling layers on state-of-the-art models. The experiments involve five recently proposed models. Significantly, the choice of pooling layers goes beyond mere classification improvement; it also addresses overfitting. The experimental results reveal significant diversity based on the selected pooling layers, namely the maximum, average, and mixed pooling, emphasizing the importance of optimizing objectives when choosing a particular pooling approach. This highlights the evolving nature of this field of study and the need for careful consideration in pooling layer selection for effective steganalysis.