Skip to content

hadder10/hadder-federated-gradient-privacy

Repository files navigation

Federated Learning Gradient Privacy System

Research-oriented system for evaluating privacy protection methods in federated learning.

The project compares three training modes:

  • baseline federated learning without additional privacy protection;
  • manual gradient protection with clipping and Gaussian noise;
  • Opacus-based DP-SGD with privacy accounting.

The system also includes gradient inversion attack simulation to evaluate how well the protection methods reduce the risk of reconstructing client data from model updates.

Tech stack

Python, PyTorch, Flower, Opacus, Docker, CIFAR-100, Google Landmarks v2.

Key features

  • Federated learning with multiple clients
  • FedAvg aggregation strategy
  • Manual gradient clipping and Gaussian noise
  • Opacus integration
  • Client update saving for attack simulation
  • Gradient inversion attack experiments
  • Metrics and plots export

About

Federated learning system for image classification with gradient privacy protection and gradient inversion attack simulation.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors