Litcius/Paper detail

A Hard Label Black-box Adversarial Attack Against Graph Neural Networks

Jiaming Mu, Binghui Wang, Qi Li, Kun Sun, Mingwei Xu, Zhuotao Liu

202132 citationsDOIOpen Access PDF

Abstract

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph structure related tasks such as node classification and graph classification. However, GNNs are vulnerable to adversarial attacks. Existing works mainly focus on attacking GNNs for node classification; nevertheless, the attacks against GNNs for graph classification have not been well explored.

Topics & Concepts

Computer scienceAdversarial systemGraphNode (physics)Artificial neural networkArtificial intelligenceMachine learningTheoretical computer scienceEngineeringStructural engineeringAdversarial Robustness in Machine LearningAdvanced Graph Neural NetworksMachine Learning in Materials Science
A Hard Label Black-box Adversarial Attack Against Graph Neural Networks | Litcius