A unified framework for privacy-preserving data analysis and machine learning

Master Federated Learning in 2 Hours—Run It on Your PC!

Diffprivlib: The IBM Differential Privacy Library

Synthetic Data SDK ✨

Synthetic data generators for structured and unstructured text, featuring differentially private learning.

The Python Differential Privacy Library. Built on top of: https://github.com/google/differential-privacy

Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )

Simulate a federated setting and run differentially private federated learning.

Paper notes and code for differentially private machine learning

Tools and service for differentially private processing of tabular and relational data

Privacy Engineering Collaboration Space

Cross-silo Federated Learning playground in Python. Discover 7 real-world federated datasets to test your new FL strategies and try to beat the leaderboard.

Differential private machine learning

A codebase that makes differentially private training of transformers easy.

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

A toolbox for differentially private data generation

Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)

Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024 Spotlight]

A Simulator for Privacy Preserving Federated Learning

A library to generate synthetic tabular or RDF data using Conditional Generative Adversary Networks (GANs) combined with Differential Privacy techniques.