RIDA: A Robust Attack Framework on Incomplete Graphs
This addresses the vulnerability of GNNs to attacks in incomplete graph settings, which is an incremental advance for researchers developing robust models.
The paper tackles the problem of adversarial attacks on Graph Neural Networks (GNNs) in real-world incomplete graph scenarios, introducing RIDA as the first robust gray-box poisoning attack framework that achieves high attack performance, as demonstrated by outperforming 9 state-of-the-art baselines on 3 real-world datasets.
Graph Neural Networks (GNNs) are vital in data science but are increasingly susceptible to adversarial attacks. To help researchers develop more robust GNN models, it's essential to focus on designing strong attack models as foundational benchmarks and guiding references. Among adversarial attacks, gray-box poisoning attacks are noteworthy due to their effectiveness and fewer constraints. These attacks exploit GNNs' need for retraining on updated data, thereby impacting their performance by perturbing these datasets. However, current research overlooks the real-world scenario of incomplete graphs. To address this gap, we introduce the Robust Incomplete Deep Attack Framework (RIDA). It is the first algorithm for robust gray-box poisoning attacks on incomplete graphs. The approach innovatively aggregates distant vertex information and ensures powerful data utilization. Extensive tests against 9 SOTA baselines on 3 real-world datasets demonstrate that RIDA's superiority in handling incompleteness and high attack performance on the incomplete graph.