典型文献
Defense against local model poisoning attacks to byzantine-robust federated learning
文献摘要：
1 Introduction
As a new mode of distributed learning,Federated Learning(FL)helps multiple organizations or clients to jointly train an artificial intelligence model without sharing their own datasets.Compared with the model trained by each client alone,a high-accuracy federated model can be obtained after multiple communication rounds in FL.Due to the charac-teristics of privacy protection and distributed learning,FL has been applied in many fields,such as the prognosis of pan-demic diseases,smart manufacturing systems,etc.
文献关键词：
中图分类号：
作者姓名：
Shiwei LU;Ruihu LI;Xuan CHEN;Yuena MA
作者机构：
Department of Basic Sciences,Air Force Engineering University,Xi'an 710051,China
文献出处：
引用格式：
[1]Shiwei LU;Ruihu LI;Xuan CHEN;Yuena MA-.Defense against local model poisoning attacks to byzantine-robust federated learning)[J].计算机科学前沿,2022(06):163-165
A类：
B类：
Defense,against,local,model,poisoning,attacks,byzantine,robust,federated,learning,Introduction,
As,new,distributed,Federated,Learning,FL,helps,multiple,organizations,clients,jointly,artificial,intelligence,without,sharing,their,own,datasets,Compared,trained,each,alone,high,accuracy,can,obtained,after,communication,rounds,Due,charac,teristics,privacy,protection,has,been,applied,many,fields,such,prognosis,pan,demic,diseases,smart,manufacturing,systems,etc
AB值：
0.745657
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
