Adversarial Attacks on Graph Neural Networks via Meta Learning

Authors: Daniel Zügner, Stephan Günnemann
Published: 2019-02-22 | Updated: 2024-01-28

Source: https://arxiv.org/abs/1902.08412

PDF: https://arxiv.org/pdf/1902.08412

Labels Predicted by AI

敵対的サンプル 敵対的攻撃手法 グラフ構築

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Deep learning models for graphs have advanced the state of the art on many tasks. Despite their recent success, little is known about their robustness. We investigate training time attacks on graph neural networks for node classification that perturb the discrete graph structure. Our core principle is to use meta-gradients to solve the bilevel problem underlying training-time attacks, essentially treating the graph as a hyperparameter to optimize. Our experiments show that small graph perturbations consistently lead to a strong decrease in performance for graph convolutional networks, and even transfer to unsupervised embeddings. Remarkably, the perturbations created by our algorithm can misguide the graph neural networks such that they perform worse than a simple baseline that ignores all relational information. Our attacks do not assume any knowledge about or access to the target classifiers.