Model Stealing Attacks Against Inductive Graph Neural Networks

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs, which can generalize to unseen data, become mainstream in th...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings - IEEE Symposium on Security and Privacy S. 1175 - 1192
Hauptverfasser:	Shen, Yun, He, Xinlei, Han, Yufei, Zhang, Yang
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.05.2022
Schlagworte:	Benchmark testing Computational modeling Data models Graph neural networks Machine learning Privacy Reconstruction algorithms
ISSN:	2375-1207
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!