blades 0.1.123

A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning

Installation

git clone https://github.com/lishenghui/blades
cd blades
pip install -v -e .
# "-v" means verbose, or more output
# "-e" means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.

cd blades/blades
python train.py file ./tuned_examples/fedsgd_cnn_fashion_mnist.yaml

Blades internally calls ray.tune; therefore, the experimental results are output to its default directory: ~/ray_results.

Experiment Results

Cluster Deployment

To run blades on a cluster, you only need to deploy Ray cluster according to the official guide.

Built-in Implementations

In detail, the following strategies are currently implemented:

Data Partitioners:

Dirichlet Partitioner

Sharding Partitioner

Citation

Please cite our paper (and the respective papers of the methods used) if you use this code in your own work:

@article{li2023blades,
  title={Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning},
  author= {Li, Shenghui and Ju, Li and Zhang, Tianru and Ngai, Edith and Voigt, Thiemo},
  journal={arXiv preprint arXiv:2206.05359},
  year={2023}
}