Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields
This addresses the problem of adversarial robustness in GNNs for real-world applications, but it is incremental as it builds on existing defense techniques by focusing on the inference stage.
The paper tackles the vulnerability of Graph Neural Networks (GNNs) to adversarial attacks by introducing RobustCRF, a post-hoc method that enhances robustness during inference without requiring model architecture knowledge, achieving validation across various models and benchmark datasets.
Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns about their real-world applicability. While existing defense techniques primarily concentrate on the training phase of GNNs, involving adjustments to message passing architectures or pre-processing methods, there is a noticeable gap in methods focusing on increasing robustness during inference. In this context, this study introduces RobustCRF, a post-hoc approach aiming to enhance the robustness of GNNs at the inference stage. Our proposed method, founded on statistical relational learning using a Conditional Random Field, is model-agnostic and does not require prior knowledge about the underlying model architecture. We validate the efficacy of this approach across various models, leveraging benchmark node classification datasets.