当前位置:
X-MOL 学术
›
IEEE Secur. Priv.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Taxonomy of Attacks on Federated Learning
IEEE Security & Privacy ( IF 1.9 ) Pub Date : 2020-12-25 , DOI: 10.1109/msec.2020.3039941 Malhar S. Jere 1 , Tyler Farnan , Farinaz Koushanfar 2
IEEE Security & Privacy ( IF 1.9 ) Pub Date : 2020-12-25 , DOI: 10.1109/msec.2020.3039941 Malhar S. Jere 1 , Tyler Farnan , Farinaz Koushanfar 2
Affiliation
Federated learning is a privacy-by-design framework that enables training deep neural networks from decentralized sources of data, but it is fraught with innumerable attack surfaces. We provide a taxonomy of recent attacks on federated learning systems and detail the need for more robust threat modeling in federated learning environments.
中文翻译:
联合学习攻击的分类法
联合学习是一种按设计保护隐私的框架,可以从分散的数据源中训练深度神经网络,但是它充满了无数的攻击面。我们提供了对联合学习系统近期攻击的分类,并详细说明了在联合学习环境中需要更强大的威胁建模的需求。
更新日期:2020-12-25
中文翻译:
联合学习攻击的分类法
联合学习是一种按设计保护隐私的框架,可以从分散的数据源中训练深度神经网络,但是它充满了无数的攻击面。我们提供了对联合学习系统近期攻击的分类,并详细说明了在联合学习环境中需要更强大的威胁建模的需求。