GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

by   Xiang Zhang, et al.

Deep learning methods for graphs achieve remarkable performance on many tasks. However, despite the proliferation of such methods and their success, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs). Here, we develop GNNGuard, a general defense approach against a variety of training-time attacks that perturb the discrete graph structure. GNNGuard can be straightforwardly incorporated into any GNN. Its core principle is to detect and quantify the relationship between the graph structure and node features, if one exists, and then exploit that relationship to mitigate negative effects of the attack. GNNGuard uses network theory of homophily to learn how best assign higher weights to edges connecting similar nodes while pruning edges between unrelated nodes. The revised edges then allow the underlying GNN to robustly propagate neural messages in the graph. GNNGuard introduces two novel components, the neighbor importance estimation, and the layer-wise graph memory, and we show empirically that both components are necessary for a successful defense. Across five GNNs, three defense methods, and four datasets, including a challenging human disease graph, experiments show that GNNGuard outperforms existing defense approaches by 15.3 state-of-the-art performance of GNNs in the face of various adversarial attacks, including targeted and non-targeted attacks.


page 1

page 2

page 3

page 4


GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks

Graph neural networks (GNNs) have been increasingly deployed in various ...

RoGAT: a robust GNN combined revised GAT with adjusted graphs

Graph Neural Networks(GNNs) are useful deep learning models to deal with...

Adversarial Attacks on Graph Neural Networks via Meta Learning

Deep learning models for graphs have advanced the state of the art on ma...

Are All Edges Necessary? A Unified Framework for Graph Purification

Graph Neural Networks (GNNs) as deep learning models working on graph-st...

Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket

Graph Lottery Ticket (GLT), a combination of core subgraph and sparse su...

DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder

Graph neural networks (GNNs) achieve remarkable performance for tasks on...

Improving Robustness of Graph Neural Networks with Heterophily-Inspired Designs

Recent studies have exposed that many graph neural networks (GNNs) are s...

Please sign up or login with your details

Forgot password? Click here to reset