MPHM: Model poisoning attacks on federal learning using historical information momentum

MPHM: Model poisoning attacks on federal learning using historical information momentum

Federated learning(FL) development has grown increasingly strong with the increased emphasis on data for individuals and industry. Federated learning allows individual participants to jointly train a global model without sharing local data, which significantly enhances data privacy. However, federat...

Full description

Bibliographic Details
Main Authors: Shi Lei, Chen Zhen, Shi Yucheng, Wei Lin, Tao Yongcai, He Mengyang, Wang Qingxian, Zhou Yuan, Gao Yufei
Format: Article
Language:English
Published: EDP Sciences 2023-01-01
Series:Security and Safety
Subjects:
federated learning
poisoning attacks
security
privacy
Online Access:https://sands.edpsciences.org/articles/sands/full_html/2023/01/sands20220018/sands20220018.html

Internet

https://sands.edpsciences.org/articles/sands/full_html/2023/01/sands20220018/sands20220018.html

Similar Items