Skip to content
Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)
Python
Branch: master
Clone or download
Latest commit 78a55ac Mar 18, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
models Code commit. Dec 17, 2018
utils Code commit. Dec 17, 2018
.gitignore Code commit. Dec 17, 2018
LICENSE Initial commit Dec 12, 2018
README.md updated readme Mar 17, 2019
helper.py updated to run with PT 1.0 Mar 17, 2019
image_helper.py updated to run with PT 1.0 Mar 17, 2019
requirements.txt updated to run with PT 1.0 Mar 17, 2019
text_helper.py updated to run with PT 1.0 Mar 17, 2019
training.py updated to run with PT 1.0 Mar 17, 2019

README.md

backdoor_federated_learning

This code includes experiments for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)

All experiments are done using Python 3.6 and PyTorch 1.0.

mkdir saved_models

python training.py --params utils/params.yaml

This is pretty raw version of the code and I encourage to contact me (eugene@cs.cornell.edu) or raise Issues in GitHub, so I can provide more details and fix bugs.

Most of the experiments resulted by tweaking parameters in utils/params.yaml (for images) and utils/words.yaml (for text), you can play with them yourself.

You can’t perform that action at this time.