StegGNN：学习图像隐写的图形表示
StegGNN: Learning Graphical Representation for Image Steganography
AI总结：
本研究提出StegGNN，一种基于图神经网络的自编码器图像隐写框架，通过将图像建模为图结构，在标准基准上达到与CNN方法相当的视觉质量和不可感知性，展示了GNN作为隐写嵌入表示的潜力。
AI中文摘要：
图像隐写是指在保持不可感知性的前提下，将秘密信息嵌入到封面图像中。近年来，深度学习的进展——主要由卷积神经网络（CNN）以及诸如逆神经网络、自编码器和生成对抗网络等架构推动——已取得了显著进步。然而，这些框架主要基于CNN架构构建，而CNN将图像视为规则网格，并受限于其感受野大小和对空间局部性的偏置。与此同时，图神经网络（GNN）最近在多项计算机视觉任务中展现出强大的适应性，并凭借诸如Vision GNN（ViG）等架构取得了最先进的性能。本研究朝这一方向迈进，引入了StegGNN——一种基于GNN的新型自编码器架构、封面无关的图像隐写框架。通过将图像建模为图结构，我们的方法利用了GNN相对于传统CNN基于网格的刚性所具有的表征灵活性。我们在标准基准数据集上进行了大量实验，以评估视觉质量和不可感知性。结果表明，我们基于GNN的方法与现有CNN基准的性能相当。这些发现表明，GNN为隐写嵌入提供了一种有前景的替代表示，并为基于深度学习的隐写领域进一步探索基于GNN的架构开辟了道路。
英文摘要：
Image steganography refers to embedding secret messages within cover images while maintaining imperceptibility. Recent advances in deep learning - primarily driven by Convolutional Neural Networks (CNNs) and architectures such as inverse neural networks, autoencoders, and generative adversarial networks - have led to notable progress. However, these frameworks are primarily built on CNN architectures, which treat images as regular grids and are limited by their receptive field size and a bias toward spatial locality. In parallel, Graph Neural Networks (GNNs) have recently demonstrated strong adaptability in several computer vision tasks, achieving state-of-the-art performance with architectures such as Vision GNN (ViG). This work moves in that direction and introduces StegGNN - a novel autoencoder-based, cover-agnostic image steganography framework based on GNNs. By modeling images as graph structures, our approach leverages the representational flexibility of GNNs over the grid-based rigidity of conventional CNNs. We conduct extensive experiments on standard benchmark datasets to evaluate visual quality and imperceptibility. Our results show that our GNN-based method performs comparably to existing CNN benchmarks. These findings suggest that GNNs provide a promising alternative representation for steganographic embedding and open the field of deep learning-based steganography to further exploration of GNN-based architectures.
