Graph Representation Learning for Spatial Image Steganalysis
This work addresses steganalysis for security applications, but it is incremental as it adapts existing graph learning methods to a specific domain.
The paper tackles the problem of detecting hidden messages in images (steganalysis) by proposing a graph representation learning architecture that models images as graphs with patches as nodes and local relationships as edges, achieving competitive performance compared to benchmark CNN models.
In this paper, we introduce a graph representation learning architecture for spatial image steganalysis, which is motivated by the assumption that steganographic modifications unavoidably distort the statistical characteristics of the hidden graph features derived from cover images. In the detailed architecture, we translate each image to a graph, where nodes represent the patches of the image and edges indicate the local relationships between the patches. Each node is associated with a feature vector determined from the corresponding patch by a shallow convolutional neural network (CNN) structure. By feeding the graph to an attention network, the discriminative features can be learned for efficient steganalysis. Experiments indicate that the reported architecture achieves a competitive performance compared to the benchmark CNN model, which has shown the potential of graph learning for steganalysis.