Recent linguistic steganalysis methods model texts as sequences and use deep learning models to extract discriminative features for detecting the presence of secret information in texts. However, natural language has a complex syntactic structure and sequences have limited representation ability for text modeling. Moreover, previous methods tend to extract features from local continuous word sequences, which cannot effectively model global characteristics. In this paper, we present a linguistic steganalysis method with graph neural network. In the proposed method, texts are translated as directed graphs with the associated information, where nodes denote words and edges show associations between the words. By training a graph convolutional network for feature extraction, each node of a graph can collect contextual information to update self-expression, accordingly effectively solving the problem of poor representation of polysemous words. Meanwhile, we adopt a globally-shared matrix to record correlation strengths between words so that each text can effectively utilize the global information to obtain the better self-representation. Experimental results have shown that the proposed work achieves the state-of-the-art performance comparing with the previous works.

中文翻译：

---

图神经网络的语言隐写分析

最近的语言隐写分析方法将文本建模为序列，并使用深度学习模型来提取判别特征，以检测文本中是否存在秘密信息。然而，自然语言具有复杂的句法结构，并且序列具有有限的文本建模表示能力。此外，先前的方法倾向于从局部连续单词序列中提取特征，而这些特征无法有效地对全局特征进行建模。在本文中，我们提出了一种基于图神经网络的语言隐写分析方法。在所提出的方法中，将文本翻译为带有相关信息的有向图，其中节点表示单词，边表示单词之间的关联。通过训练图卷积网络进行特征提取，图的每个节点都可以收集上下文信息以更新自我表达，从而有效地解决了多义词表示能力差的问题。同时，我们采用全局共享矩阵来记录单词之间的关联强度，以便每个文本都可以有效地利用全局信息以获得更好的自我表示。实验结果表明，与以前的工作相比，拟议的工作达到了最先进的性能。