/Federated-Learning-with-Local-Differential-Privacy

Differential priavcy based federated learning framework by various neural networks and svm using PyTorch.

Primary LanguagePython

Federated Learning with Local Differential Privacy

Citation

If you find "federated learning with local DP" useful in your research, please consider citing:

@ARTICLE{kang2020fed,
author={Wei, Kang and Li, Jun and Ding, Ming and Ma, Chuan and Yang, Howard H. and Farokhi, Farhad and Jin, Shi and Quek, Tony Q. S. and Poor, H. Vincent},
journal={IEEE Transactions on Information Forensics and Security}, 
title={Federated Learning With Differential Privacy: {Algorithms} and Performance Analysis}, 
year={2020},
volume={15},
number={},
pages={3454-3469},}

@ARTICLE{Wei2021User,
author={K. {Wei} and J. {Li} and M. {Ding} and C. {Ma} and H. {Su} and B. {Zhang} and H. V. {Poor}},
journal={IEEE Transactions on Mobile Computing}, 
title={User-Level Privacy-Preserving Federated Learning: {Analysis} and Performance Optimization}, 
year={2021},
volume={},
number={},
pages={1-1},}}

@ARTICLE{Ma202On,
author={C. {Ma} and J. {Li} and M. {Ding} and H. H. {Yang} and F. {Shu} and T. Q. S. {Quek} and H. V. {Poor}},
title={On Safeguarding Privacy and Security in the Framework of Federated Learning},
journal   = {{IEEE} Network},
volume    = {34},
number    = {4},
pages     = {242-248},
year      = {2020},}

Prerequisites

Python 3.6
Torch 1.5.1

Models&Data

Learning models: CNN, MLP and SVM
Datasets: Mnist and Adult

Training

Description