526互联

leakage

论文阅读 | Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective

Soteria:基于表示的联邦学习中可证明的隐私泄露防御https://ieeexplore.ieee.org/document/9578192 # 3 FL隐私泄露的根本原因 ## 3.1 FL中的表示层信息泄露 **问题设置** 在FL中，有多个设备和一个中央服务器。服务器协调FL进程，其中每个 ......
Representation Perspective Federated Provable Learning

【五期邹昱夫】arXiv(22)iDLG: Improved Deep Leakage from Gradients

"Zhao B, Mopuri K R, Bilen H. idlg: Improved deep leakage from gradients[J]. arXiv preprint arXiv:2001.02610, 2020." 本文发现共享梯度肯定会泄露数据真实标签。我们提出了一种简单但可靠的 ......
Gradients Improved Leakage arXiv Deep

【五期邹昱夫】CCF-A（NeurIPS'19）Deep leakage from gradients.

"Zhu, Ligeng, Zhijian Liu, and Song Han. "Deep leakage from gradients." Advances in neural information processing systems 32 (2019)." 本文从公开共享的梯度中获得私有训 ......
gradients NeurIPS leakage CCF-A Deep
共3篇  :1/1页 首页上一页1下一页尾页