Skip to main content

Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks

Publication ,  Conference
Jia, Y; Zou, D; Wang, H; Jin, H
Published in: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
August 6, 2023

Graph neural networks (GNNs) have shown considerable promise for graph-structured data. However, they are also known to be unstable and vulnerable to perturbations and attacks. Recently, the Lipschitz constant has been adopted as a control on the stability of Euclidean neural networks, but calculating the exact constant is also known to be difficult even for very shallow networks. In this paper, we extend the Lipschitz analysis to graphs by providing a systematic scheme for estimating upper bounds of the Lipschitz constants of GNNs. We also derive concrete bounds for widely used GNN architectures including GCN, GraphSAGE and GAT. We then use these Lipschitz bounds for regularized GNN training for improved stability. Our numerical results on Lipschitz regularization of GNNs not only illustrate enhanced test accuracy under random noise, but also show consistent improvement for state-of-the-art defense methods against adversarial attacks.

Duke Scholars

Published In

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

DOI

ISBN

9798400701030

Publication Date

August 6, 2023

Start / End Page

951 / 963
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Jia, Y., Zou, D., Wang, H., & Jin, H. (2023). Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 951–963). https://doi.org/10.1145/3580305.3599335
Jia, Y., D. Zou, H. Wang, and H. Jin. “Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks.” In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 951–63, 2023. https://doi.org/10.1145/3580305.3599335.
Jia Y, Zou D, Wang H, Jin H. Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2023. p. 951–63.
Jia, Y., et al. “Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks.” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2023, pp. 951–63. Scopus, doi:10.1145/3580305.3599335.
Jia Y, Zou D, Wang H, Jin H. Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2023. p. 951–963.

Published In

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

DOI

ISBN

9798400701030

Publication Date

August 6, 2023

Start / End Page

951 / 963