Label flipping adversarial attack on graph neural network
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...
Gorde:
| Egile Nagusiak: | , , |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Chinês |
| Argitaratua: |
Editorial Department of Journal on Communications
2021-09-01
|
| Saila: | Tongxin xuebao |
| Gaiak: | |
| Sarrera elektronikoa: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021167/ |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|