Cargando…
A Lightweight Method for Defense Graph Neural Networks Adversarial Attacks
Graph neural network has been widely used in various fields in recent years. However, the appearance of an adversarial attack makes the reliability of the existing neural networks challenging in application. Premeditated attackers, can make very small perturbations to the data to fool the neural net...
Autores principales: | Qiao, Zhi, Wu, Zhenqiang, Chen, Jiawang, Ren, Ping’an, Yu, Zhiliang |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9858433/ https://www.ncbi.nlm.nih.gov/pubmed/36673179 http://dx.doi.org/10.3390/e25010039 |
Ejemplares similares
-
Enhanced Signed Graph Neural Network with Node Polarity
por: Chen, Jiawang, et al.
Publicado: (2022) -
Defense against membership inference attack in graph neural networks through graph perturbation
por: Wang, Kai, et al.
Publicado: (2022) -
Improving the adversarial transferability with relational graphs ensemble adversarial attack
por: Pi, Jiatian, et al.
Publicado: (2023) -
Derivative-free optimization adversarial attacks for graph convolutional networks
por: Yang, Runze, et al.
Publicado: (2021) -
Transferability of features for neural networks links to adversarial attacks and defences
por: Kotyan, Shashank, et al.
Publicado: (2022)