https://github.com/secretflow/secretflow

A unified framework for privacy-preserving data analysis and machine learning
https://github.com/secretflow/secretflow

confidential-computing data-analysis differential-privacy federated-learning homomorphic-encryption machine-learning privacy-preserving private-set-intersection secure-multiparty-computation split-learning trusted-execution-environment

Last synced: 4 days ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/secretflow/secretflow
• Owner: secretflow
• License: apache-2.0
• Created: 2022-04-15T09:07:44.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-10-29T10:06:17.000Z (10 days ago)
• Last Synced: 2024-10-29T12:11:41.645Z (10 days ago)
• Topics: confidential-computing, data-analysis, differential-privacy, federated-learning, homomorphic-encryption, machine-learning, privacy-preserving, private-set-intersection, secure-multiparty-computation, split-learning, trusted-execution-environment
• Language: Python
• Homepage: https://www.secretflow.org.cn/docs/secretflow/en/
• Size: 198 MB
• Stars: 2,340
• Watchers: 50
• Forks: 388
• Open Issues: 159
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS
  • Security: SECURITY.md

Awesome Lists containing this project

• awesome-privacy-engineering - SecretFlow - SecretFlow is a unified framework for privacy-preserving data analysis and machine learning. (Awesome Privacy Engineering [](https://awesome.re) / Machine Learning and Algorithmic Bias)
• Awesome-SGX-Open-Source - https://github.com/secretflow/secretflow
• awesome-identity - Secretflow - preserving data intelligence and machine learning (MPC-based Solutions / General MPC Frameworks)
• FLsystem-paper - `Github`

README

        


    



---

[![CircleCI](https://dl.circleci.com/status-badge/img/gh/secretflow/secretflow/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/secretflow/secretflow/tree/main)



简体中文｜English



SecretFlow is a unified framework for privacy-preserving data intelligence and machine learning. To achieve this goal,

it provides:

- An abstract device layer consists of plain devices and secret devices which encapsulate various cryptographic protocols.

- A device flow layer modeling higher algorithms as device object flow and DAG.

- An algorithm layer to do data analysis and machine learning with horizontal or vertical partitioned data.

- A workflow layer that seamlessly integrates data processing, model training, and hyperparameter tuning.



    



## Documentation

- [SecretFlow](https://www.secretflow.org.cn/docs/secretflow/en/)

  - [Getting Started](https://www.secretflow.org.cn/docs/secretflow/en/getting_started/index.html)

  - [User Guide](https://www.secretflow.org.cn/docs/secretflow/en/user_guide/index.html)

  - [API Reference](https://www.secretflow.org.cn/docs/secretflow/en/api/index.html)

  - [Tutorial](https://www.secretflow.org.cn/docs/secretflow/en/tutorial/index.html)

## SecretFlow Related Projects

- [Kuscia](https://github.com/secretflow/kuscia): A lightweight privacy-preserving computing task orchestration framework based on K3s.

- [SCQL](https://github.com/secretflow/scql): A system that allows multiple distrusting parties to run joint analysis without revealing their private data.

- [SPU](https://github.com/secretflow/spu): A provable, measurable secure computation device, which provides computation ability while keeping your private data protected.

- [HEU](https://github.com/secretflow/heu): A high-performance homomorphic encryption algorithm library.

- [YACL](https://github.com/secretflow/yacl): A C++ library that contains cryptography, network and io modules which other SecretFlow code depends on.

## Install

Please check [INSTALLATION.md](./docs/getting_started/installation.md)

## Deployment

Please check [DEPLOYMENT.md](./docs/getting_started/deployment.md)

## Learn PETs

We also provide a curated list of papers and SecretFlow's tutorials on Privacy-Enhancing Technologies (PETs).

Please check [AWESOME-PETS.md](./docs/awesome-pets/awesome-pets.md)

## Contributing

Please check [CONTRIBUTING.md](./CONTRIBUTING.md)

## Benchmarks

Please check [OVERALL_BENCHMARK.md](./docs/developer/benchmark/overall_benchmark.md)

## Disclaimer

Non-release versions of SecretFlow are prohibited from using in any production environment due to possible bugs, glitches, lack of functionality, security issues or other problems.