Unifying Adversarial Perturbation for Graph Neural Networks
By: Jinluan Yang , Ruihao Zhang , Zhengyu Chen and more
Potential Business Impact:
Makes smart computer networks harder to trick.
This paper studies the vulnerability of Graph Neural Networks (GNNs) to adversarial attacks on node features and graph structure. Various methods have implemented adversarial training to augment graph data, aiming to bolster the robustness and generalization of GNNs. These methods typically involve applying perturbations to the node feature, weights, or graph structure and subsequently minimizing the loss by learning more robust graph model parameters under the adversarial perturbations. Despite the effectiveness of adversarial training in enhancing GNNs' robustness and generalization abilities, its application has been largely confined to specific datasets and GNN types. In this paper, we propose a novel method, PerturbEmbedding, that integrates adversarial perturbation and training, enhancing GNNs' resilience to such attacks and improving their generalization ability. PerturbEmbedding performs perturbation operations directly on every hidden embedding of GNNs and provides a unified framework for most existing perturbation strategies/methods. We also offer a unified perspective on the forms of perturbations, namely random and adversarial perturbations. Through experiments on various datasets using different backbone models, we demonstrate that PerturbEmbedding significantly improves both the robustness and generalization abilities of GNNs, outperforming existing methods. The rejection of both random (non-targeted) and adversarial (targeted) perturbations further enhances the backbone model's performance.
Similar Papers
Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
Machine Learning (CS)
Makes computer networks safer from sneaky attacks.
Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
Machine Learning (CS)
Protects smart computer networks from sneaky attacks.
$β$-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation
Machine Learning (CS)
Makes computer programs stronger against mistakes.