XFL is a lightweight, high-performance federated learning framework supporting both horizontal and vertical FL. It integrates homomorphic encryption, DP, secure MPC, and optimizes network resilience. Compatible with major ML libraries and deployable via Docker or Conda.

Features

  • Supports horizontal and vertical federated learning models
  • Implements homomorphic encryption, differential privacy, MPC
  • Optimized for high latency, packet loss, unstable network
  • Can run with CPU, GPU, or hybrid nodes
  • Integrates with PyTorch, TensorFlow, PaddlePaddle, JAX
  • Easy deployment in Docker or Conda environments

Project Samples

Xfl Screenshot 1

Project Activity

See All Activity >