联邦学习安全与隐私保护研究综述

周俊, 方国英, 吴楠 - 西华大学学报(自然科学版), 2020 - xhuqk.com
数据孤岛以及模型训练和应用过程中的隐私泄露是当下阻碍人工智能技术发展的主要难题.
联邦学习作为一种高效的隐私保护手段应运而生. 联邦学习是一种分布式的机器学习方法 …

Survey on security and privacy of federated learning models

顾育豪, 白跃彬 - Journal of Software, 2022 - jos.org.cn
随着数据孤岛现象的出现和个人隐私保护的重视, 集中学习的应用模式受到制约,
而联邦学习作为一个分布式机器学习框架, 可以在不泄露用户数据的前提下完成模型训练 …

Privacy-preserving techniques in federated learning

刘艺璇, 陈红, 刘宇涵, 李翠平 - Journal of Software, 2021 - jos.org.cn
联邦学习是顺应大数据时代和人工智能技术发展而兴起的一种协调多个参与方共同训练模型的
机制. 它允许各个参与方将数据保留在本地, 在打破数据孤岛的同时保证参与方对数据的控制权 …

Survey on security and privacy-preserving in federated learning

Z Jun, F Guoying, WU Nan - Journal of Xihua University (Natural Science …, 2020 - xhuqk.com
The issue of data island has always been a difficult problem during the development of
artificial intelligence. The risk of privacy disclosure in model training and application further …

[PDF][PDF] 联邦学习模型安全与隐私研究进展

顾育豪, 白跃彬 - 软件学报, 2022 - jos.org.cn
随着数据孤岛现象的出现和个人隐私保护的重视, 集中学习的应用模式受到制约,
而联邦学习作为一个分布式机器学习框架, 可以在不泄露用户数据的前提下完成模型训练 …

Research progress of privacy issues in federated learning

汤凌韬, 陈左宁, 张鲁飞, 吴东 - Journal of Software, 2021 - jos.org.cn
随着大数据, 云计算等领域的蓬勃发展, 重视数据安全与隐私已经成为世界性的趋势,
不同团体为保护自身利益和隐私不愿贡献数据, 形成了数据孤岛. 联邦学习使数据不出本地就可 …

Survey on private model publishing for federated learning

S Congcong, G Xianzhou, H Xiuli… - Nanjing Xinxi …, 2022 - search.proquest.com
Federated learning is a kind of distributed machine learning technology to ensure that local
data is not compromised when training with big data for machine learning models. However …

[PDF][PDF] 联邦学习中的隐私保护技术

刘艺璇, 陈红, 刘宇涵, 李翠平 - 软件学报, 2021 - jos.org.cn
联邦学习是顺应大数据时代和人工智能技术发展而兴起的一种协调多个参与方共同训练模型的
机制. 它允许各个参与方将数据保留在本地, 在打破数据孤岛的同时保证参与方对数据的控制权 …

[HTML][HTML] Privacy and security in federated learning: A survey

R Gosselin, L Vieu, F Loukil, A Benoit - Applied Sciences, 2022 - mdpi.com
In recent years, privacy concerns have become a serious issue for companies wishing to
protect economic models and comply with end-user expectations. In the same vein, some …

Closing the loophole: rethinking reconstruction attacks in federated learning from a privacy standpoint

SH Na, HG Hong, J Kim, S Shin - … of the 38th Annual Computer Security …, 2022 - dl.acm.org
Federated Learning was deemed as a private distributed learning framework due to the
separation of data from the central server. However, recent works have shown that privacy …