CLB-Defense: based on contrastive learning defense for graph neural network against backdoor attack

CLB-Defense: based on contrastive learning defense for graph neural network against backdoor attack

Show other versions (1)

For the problem that the existing backdoor attack defense methods are difficult to deal with irregular and unstructured discrete graph data to alleviate the threat of backdoor attacks, a backdoor attack defense method for GNN based on contrastive learning was proposed, namely CLB-Defense.Specificall...

Full description

Bibliographic Details
Main Authors: Jinyin CHEN, Haiyang XIONG, Haonan MA, Yayu ZHENG
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2023-04-01
Series:Tongxin xuebao
Subjects:
graph neural network
backdoor attack
robustness
defense
contrastive learning
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023074/

Internet

http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023074/

Similar Items