Toward Efficient Defense Against Model Poisoning Attacks in Privacy-Preserving Federated Learning

This repository contains PyTorch implementation of the paper: Toward Efficient Defense Against Model Poisoning Attacks in Privacy-Preserving Federated Learning.

Paper

Toward Efficient Defense Against Model Poisoning Attacks in Privacy-Preserving Federated Learning

Content

The repository contains one jupyter notebook for each benchmark which can be used to re-produce the experiments reported in the paper for that benchmark. The notebooks contain clear instructions on how to run the experiments.

Data sets

MNIST and CIFAR10 will be automatically downloaded.

Dependencies

Python 3.6

PyTorch 1.6

TensorFlow 2

Results

The results can be seen in the paper