Cargando…

Derivative-free optimization adversarial attacks for graph convolutional networks

In recent years, graph convolutional networks (GCNs) have emerged rapidly due to their excellent performance in graph data processing. However, recent researches show that GCNs are vulnerable to adversarial attacks. An attacker can maliciously modify edges or nodes of the graph to mislead the model’...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Runze, Long, Teng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8409335/
https://www.ncbi.nlm.nih.gov/pubmed/34541312
http://dx.doi.org/10.7717/peerj-cs.693