Join Our Discord (630+ Members)

15 Privacy-Preserving and Federated Learning Frameworks and Libraries for Secure Machine Learning

Explore open source privacy-preserving and federated learning frameworks and libraries for secure machine learning, ensuring data confidentiality.

Open Source Privacy-Preserving ML Frameworks

  • BastionLab

    BastionLab is a framework for confidential data science collaboration. It uses Confidential Computing, Access control data science, and Differential Privacy to enable data scientists to remotely perform data exploration, statistics, and training on confidential data while ensuring maximal privacy for data owners.

    License: Apache License 2.0

  • Concrete-ML

    Concrete-ML is a Privacy-Preserving Machine Learning (PPML) open-source set of tools built on top of The Concrete Framework by Zama . It aims to simplify the use of fully homomorphic encryption (FHE) for data scientists to help them automatically turn machine learning models into their homomorphic equivalent.

    License: Other

  • Concrete-ML

    Fedlearner is collaborative machine learning framework that enables joint modeling of data distributed between institutions.

    License: Apache License 2.0

  • FATE

    FATE (Federated AI Technology Enabler) is the world’s first industrial grade federated learning open source framework to enable enterprises and institutions to collaborate on data while protecting data security and privacy.

    License: Apache License 2.0

  • FedML

    FedML provides a research and production integrated edge-cloud platform for Federated/Distributed Machine Learning at anywhere at any scale.

    License: Apache License 2.0

  • Flower

    Flower is a Federated Learning Framework with a unified approach. It enables the federation of any ML workload, with any ML framework, and any programming language.

    License: Apache License 2.0

  • Google's Differential Privacy

    This is a C++ library of ε-differentially private algorithms, which can be used to produce aggregate statistics over numeric data sets containing private or sensitive information.

    License: Apache License 2.0

  • Intel Homomorphic Encryption Backend

    The Intel HE transformer for nGraph is a Homomorphic Encryption (HE) backend to the Intel nGraph Compiler, Intel’s graph compiler for Artificial Neural Networks.

    License: Apache License 2.0

  • Microsoft SEAL

    Microsoft SEAL is an easy-to-use open-source (MIT licensed) homomorphic encryption library developed by the Cryptography Research group at Microsoft.

    License: MIT License

  • OpenFL

    OpenFL is a Python framework for Federated Learning. OpenFL is designed to be a flexible, extensible and easily learnable tool for data scientists. OpenFL is developed by Intel Internet of Things Group (IOTG) and Intel Labs.

    License: Apache License 2.0

  • PySyft

    A Python library for secure, private Deep Learning. PySyft decouples private data from model training, using Multi-Party Computation (MPC) within PyTorch.

    License: Apache License 2.0

  • Rosetta

    A privacy-preserving framework based on TensorFlow with customized backend Operations using Multi-Party Computation (MPC). Rosetta reuses the APIs of TensorFlow and allows to transfer original TensorFlow codes into a privacy-preserving manner with minimal changes.

    License: GNU Lesser General Public License v3.0

  • Substra

    Substra is an open-source framework for privacy-preserving, traceable and collaborative Machine Learning.

    License: Apache License 2.0

  • Tensorflow Privacy

    A Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy.

    License: Apache License 2.0

  • TF Encrypted

    A Framework for Confidential Machine Learning on Encrypted Data in TensorFlow.

    License: Apache License 2.0

Last Updated: Dec 26, 2023