TDGIA:Effective Injection Attacks on Graph Neural Networks

by   Xu Zou, et al.

Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. However, recent studies have shown that GNNs are vulnerable to adversarial attacks. In this paper, we study a recently-introduced realistic attack scenario on graphs – graph injection attack (GIA). In the GIA scenario, the adversary is not able to modify the existing link structure and node attributes of the input graph, instead the attack is performed by injecting adversarial nodes into it. We present an analysis on the topological vulnerability of GNNs under GIA setting, based on which we propose the Topological Defective Graph Injection Attack (TDGIA) for effective injection attacks. TDGIA first introduces the topological defective edge selection strategy to choose the original nodes for connecting with the injected ones. It then designs the smooth feature optimization objective to generate the features for the injected nodes. Extensive experiments on large-scale datasets show that TDGIA can consistently and significantly outperform various attack baselines in attacking dozens of defense GNN models. Notably, the performance drop on target GNNs resultant from TDGIA is more than double the damage brought by the best attack solution among hundreds of submissions on KDD-CUP 2020.


Adversarial Camouflage for Node Injection Attack on Graphs

Node injection attacks against Graph Neural Networks (GNNs) have receive...

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Recently Graph Injection Attack (GIA) emerges as a practical attack scen...

Robustness of Graph Neural Networks at Scale

Graph Neural Networks (GNNs) are increasingly important given their popu...

Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks

We present evidence for the existence and effectiveness of adversarial a...

Structack: Structure-based Adversarial Attacks on Graph Neural Networks

Recent work has shown that graph neural networks (GNNs) are vulnerable t...

Task and Model Agnostic Adversarial Attack on Graph Neural Networks

Graph neural networks (GNNs) have witnessed significant adoption in the ...

Single Node Injection Attack against Graph Neural Networks

Node injection attack on Graph Neural Networks (GNNs) is an emerging and...