ALD-GCN: Graph Convolutional Networks with Attribute-level Defense

Graph Neural Networks(GNNs), such as Graph Convolutional Network, have exhibited impressive performance on various real-world datasets. However, many researches have confirmed that deliberately designed adversarial attacks can easily confuse GNNs on the classification of target nodes (targeted attac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on big data 2024-07, p.1-12
Hauptverfasser: Li, Yihui, Guo, Yuanfang, Wang, Junfu, Nie, Shihao, Yang, Liang, Huang, Di, Wang, Yunhong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Graph Neural Networks(GNNs), such as Graph Convolutional Network, have exhibited impressive performance on various real-world datasets. However, many researches have confirmed that deliberately designed adversarial attacks can easily confuse GNNs on the classification of target nodes (targeted attacks) or all the nodes (global attacks). According to our observations, different attributes tend to be differently treated when the graph is attacked. Unfortunately, most of the existing defense methods can only defend at the graph or node level, which ignores the diversity of different attributes within each node. To address this limitation, we propose to leverage a new property, named Attribute-level Smoothness (ALS), which is defined based on the local differences of graph. We then propose a novel defense method, named GCN with Attribute-level Defense (ALD-GCN), which utilizes the ALS property to provide attribute-level protection to each attributes. Extensive experiments on real-world graphs have demonstrated the superiority of the proposed work and the potentials of our ALS property in the attacks.
ISSN:2332-7790
2332-7790
2372-2096
DOI:10.1109/TBDATA.2024.3433553