# Graph Representation Learning for Spatial Image Steganalysis

arXiv: https://arxiv.org/abs/2110.00957 · HTML: https://mlsanity.com/paper/2110.00957/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 3 Oct 2021.

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Superpixel Image Classification with Graph Attention Networks](https://mlsanity.com/paper/2002.05544/) (2020)

## Built on by (most cited first, 3 of 3)

- [Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions](https://mlsanity.com/paper/2308.04522/) (2023)
- [JPEG Steganalysis Based on Steganographic Feature Enhancement and Graph Attention Learning](https://mlsanity.com/paper/2302.02276/) (2023)
- [Hierarchical Graph Neural Network for Compressed Speech Steganalysis](https://mlsanity.com/paper/2507.21591/) (2025)

## Abstract (arXiv)

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.