LPD-EPFL/byzfl

ByzFL: A Python library for robust federated learning, offering Byzantine-resilient aggregators, attack simulations, and ML pipelines for distributed systems. Compatible with PyTorch and NumPy.

49
/ 100
Emerging

ByzFL helps machine learning researchers and practitioners simulate and test how well federated learning models perform when some participants might be malicious or unreliable. It takes your PyTorch or NumPy-based machine learning models and data, then simulates a distributed learning environment, showing you how robust your aggregation strategies are against various attacks. This tool is for researchers and engineers working on secure and robust distributed AI systems.

No commits in the last 6 months. Available on PyPI.

Use this if you need to evaluate and benchmark the resilience of federated learning algorithms against adversarial attacks in a simulated distributed environment.

Not ideal if you are looking for a federated learning framework for production deployment rather than research and simulation.

federated-learning distributed-machine-learning AI-security adversarial-AI privacy-preserving-AI
Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

34

Forks

6

Language

Python

License

MIT

Last pushed

Jul 31, 2025

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LPD-EPFL/byzfl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.