Graph Neural Networks (GNNs) have demonstrated remarkable performance across various applications, yet they are vulnerable to sophisticated adversarial attacks, particularly node injection attacks. The success of such attacks heavily relies on their stealthiness, the ability to blend in with the original graph and evade detection. However, existing methods often achieve stealthiness by relying on indirect proxy metrics, lacking consideration for the fundamental characteristics of the injected content, or focusing only on imitating local structures, which leads to the problem of local myopia. To overcome these limitations, we propose a dual-constraint stealthy node injection framework, called Joint Alignment of Nodal and Universal Structures (JANUS). At the local level, we introduce a local feature manifold alignment strategy to achieve geometric consistency in the feature space. At the global level, we incorporate structured latent variables and maximize the mutual information with the generated structures, ensuring the injected structures are consistent with the semantic patterns of the original graph. We model the injection attack as a sequential decision process, which is optimized by a reinforcement learning agent. Experiments on multiple standard datasets demonstrate that the JANUS framework significantly outperforms existing methods in terms of both attack effectiveness and stealthiness.

翻译：图神经网络（GNNs）在各种应用中展现出卓越的性能，但它们也容易受到复杂的对抗性攻击，尤其是节点注入攻击。这类攻击的成功在很大程度上依赖于其隐蔽性，即能够融入原始图结构并规避检测。然而，现有方法通常通过依赖间接的代理指标来实现隐蔽性，缺乏对注入内容基本特征的考虑，或仅专注于模仿局部结构，这导致了局部短视问题。为了克服这些限制，我们提出了一种双约束的隐蔽节点注入框架，称为节点与全局结构联合对齐（JANUS）。在局部层面，我们引入了一种局部特征流形对齐策略，以实现特征空间中的几何一致性。在全局层面，我们结合了结构化潜变量，并最大化其与生成结构之间的互信息，确保注入的结构与原始图的语义模式保持一致。我们将注入攻击建模为一个序列决策过程，并通过强化学习智能体进行优化。在多个标准数据集上的实验表明，JANUS框架在攻击有效性和隐蔽性方面均显著优于现有方法。