ByzFL: Research Framework for Robust Federated Learning

We present ByzFL, an open-source Python library for developing and benchmarking robust federated learning (FL) algorithms. ByzFL provides a unified and extensible framework that includes implementations of state-of-the-art robust aggregators, a suite of configurable attacks, and tools for simulating a variety of FL scenarios, including heterogeneous data distributions, multiple training algorithms, and adversarial threat models. The library enables systematic experimentation via a single JSON-based configuration file and includes built-in utilities for result visualization. Compatible with PyTorch tensors and NumPy arrays, ByzFL is designed to facilitate reproducible research and rapid prototyping of robust FL solutions. ByzFL is available atthis https URL, with source code hosted on GitHub:this https URL.

@article{gonzález2025_2505.24802,
  title={ ByzFL: Research Framework for Robust Federated Learning },
  author={ Marc González and Rachid Guerraoui and Rafael Pinot and Geovani Rizk and John Stephan and François Taïani },
  journal={arXiv preprint arXiv:2505.24802},
  year={ 2025 }
}