Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
This work addresses vulnerabilities in GNNs for security applications, but it is incremental as it builds on existing GIA methods.
The paper tackles the problem of improving Graph Injection Attacks (GIA) on Graph Neural Networks (GNNs) by addressing limitations of existing methods, such as reliance on surrogate models and trade-offs in attack success, and proposes QUGIA, which achieves state-of-the-art performance with unnoticeable attacks across six real-world datasets.
The robustness of Graph Neural Networks (GNNs) has become an increasingly important topic due to their expanding range of applications. Various attack methods have been proposed to explore the vulnerabilities of GNNs, ranging from Graph Modification Attacks (GMA) to the more practical and flexible Graph Injection Attacks (GIA). However, existing methods face two key challenges: (i) their reliance on surrogate models, which often leads to reduced attack effectiveness due to structural differences and prior biases, and (ii) existing GIA methods often sacrifice attack success rates in undefended settings to bypass certain defense models, thereby limiting their overall effectiveness. To overcome these limitations, we propose QUGIA, a Query-based and Unnoticeable Graph Injection Attack. QUGIA injects nodes by first selecting edges based on victim node connections and then generating node features using a Bayesian framework. This ensures that the injected nodes are similar to the original graph nodes, implicitly preserving homophily and making the attack more unnoticeable. Unlike previous methods, QUGIA does not rely on surrogate models, thereby avoiding performance degradation and achieving better generalization. Extensive experiments on six real-world datasets with diverse characteristics demonstrate that QUGIA achieves unnoticeable attacks and outperforms state-of-the-art attackers. The code will be released upon acceptance.