Graph Adversarial Attack via Rewiring
Document Type
Conference Proceeding
Publication Date
8-14-2021
Abstract
Graph Neural Networks (GNNs) have demonstrated their powerful capability in learning representations for graph-structured data. Consequently, they have enhanced the performance of many graph-related tasks such as node classification and graph classification. However, it is evident from recent studies that GNNs are vulnerable to adversarial attacks. Their performance can be largely impaired by deliberately adding carefully created unnoticeable perturbations to the graph. Existing attacking methods often produce perturbation by adding/deleting a few edges, which might be noticeable even when the number of modified edges is small. In this paper, we propose a graph rewiring operation to perform the attack. It can affect the graph in a less noticeable way compared to existing operations such as adding/deleting edges. We then utilize deep reinforcement learning to learn the strategy to effectively perform the rewiring operations. Experiments on real-world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation impacts the target model and the advantages of the rewiring operations. The implementation of the proposed framework is available at https://github.com/alge24/ReWatt.
Identifier
85114684280 (Scopus)
ISBN
[9781450383325]
Publication Title
Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
External Full Text Location
https://doi.org/10.1145/3447548.3467416
First Page
1161
Last Page
1169
Grant
CNS1815636
Fund Ref
National Science Foundation
Recommended Citation
Ma, Yao; Wang, Suhang; Derr, Tyler; Wu, Lingfei; and Tang, Jiliang, "Graph Adversarial Attack via Rewiring" (2021). Faculty Publications. 3879.
https://digitalcommons.njit.edu/fac_pubs/3879
