search

wenzhu23333 / Differential-Privacy-Based-Federated-Learning

Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )
GNU General Public License v3.0
348 stars 56 forks source link

请教 #15

Closed Speed-Fiorna closed 1 year ago

Speed-Fiorna commented 1 year ago

您好，想问一下几个问题 1.每一层能否使用不同的隐私预算进行加噪，如果用这种方式，那么总隐私消耗应该怎样计算呢 2.使用f-DP进行隐私预算的计算方法，是与RDP转(ε,δ)-DP的方法类似的嘛

wenzhu23333 commented 1 year ago

1、参考：Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning NhatHai Phan, Xintao Wu, Han Hu, Dejing Dou. IEEE ICDM'17, New Orleans, USA 18-21 November 2017. https://arxiv.org/abs/1709.05750. 2、f-dp似乎没有epsilon的概念，具体转换还需参考原文。

Speed-Fiorna commented 1 year ago

谢谢大佬指教