⚔️ Blades: A Unified Benchmark Suite for Attacks and Defenses in Federated Learning
A decentralized/P2P federated learning library
A Python simulator for decentralized federated learning systems, supporting PoW, PoS, and committee-based consensus, multiple validation and aggregation methods, and malicious trainer behaviors like label flipping. Enables IID and N-IID data setups for flexible testing and analysis of system resilience.
The provided Python script generates non-IID (non-identically independently distributed) datasets for use in federated learning simulations. Federated learning often requires data partitions to simulate real-world scenarios where data across devices or clients is unevenly distributed.
This repository is a base template for Federated Learning build using Flower with Aviation Dataset.
Add a description, image, and links to the federated-learning-simulator topic page so that developers can more easily learn about it.
To associate your repository with the federated-learning-simulator topic, visit your repo's landing page and select "manage topics."