Label flipping adversarial attack on graph neural network

Label flipping adversarial attack on graph neural network

Show other versions (1)

To expand the adversarial attack types of graph neural networks and fill the relevant research gaps, label flipping attack methods were proposed to evaluate the robustness of graph neural network aimed at label noise.The effectiveness mechanisms of adversarial attacks were summarized as three basic...

Full description

Bibliographic Details
Main Authors: Yiteng WU, Wei LIU, Hongtao YU
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2021-09-01
Series:Tongxin xuebao
Subjects:
graph neural network
adversarial attack
label flipping
attack hypothesis
robustness
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021167/

Internet

http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021167/

Similar Items