Microsoft SEAL - Homomorphic Encryption Library
webCredibility Rating
Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.
Rating inherited from publication venue: GitHub
Microsoft SEAL is a cryptographic tool relevant to AI safety insofar as it enables privacy-preserving computation; it is more directly a software engineering resource than an AI safety analysis, but has applications in secure and confidential AI deployment scenarios.
Metadata
Summary
Microsoft SEAL is an open-source homomorphic encryption library that allows computations to be performed directly on encrypted data without decryption. It supports BFV and CKKS encryption schemes, enabling privacy-preserving machine learning and secure computation applications. The library is designed for practical use in cloud and AI scenarios where data privacy is paramount.
Key Points
- •Implements homomorphic encryption schemes (BFV, CKKS) enabling arithmetic operations on encrypted data without exposing plaintext
- •Supports privacy-preserving machine learning inference, allowing models to run on encrypted user data
- •Open-source C++ library with cross-platform support, maintained by Microsoft Research
- •Relevant to AI safety and privacy in deployment contexts where sensitive data must remain confidential
- •Enables secure multi-party computation scenarios useful for federated learning and confidential AI systems
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| AI Governance Coordination Technologies | Approach | 91.0 |
Cached Content Preview
GitHub - microsoft/SEAL: Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library. · GitHub
Skip to content
You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
microsoft
/
SEAL
Public
Notifications
You must be signed in to change notification settings
Fork
762
Star
4k
main Branches Tags Go to file Code Open more actions menu Folders and files
Name Name Last commit message Last commit date Latest commit
History
1,818 Commits 1,818 Commits android android cmake cmake dotnet dotnet native native pipelines pipelines pkgconfig pkgconfig tools tools .clang-format .clang-format .gitignore .gitignore .pre-commit-config.yaml .pre-commit-config.yaml CHANGES.md CHANGES.md CMakeLists.txt CMakeLists.txt CODE_OF_CONDUCT.md CODE_OF_CONDUCT.md CONTRIBUTING.md CONTRIBUTING.md ISSUES.md ISSUES.md LICENSE LICENSE NOTICE NOTICE README.md README.md SECURITY.md SECURITY.md View all files Repository files navigation
Microsoft SEAL
Microsoft SEAL is an easy-to-use open-source ( MIT licensed ) homomorphic encryption library developed by the Cryptography and Privacy Research Group at Microsoft.
Microsoft SEAL is written in modern standard C++ and is easy to compile and run in many different environments.
For more information about the Microsoft SEAL project, see sealcrypto.org .
This document pertains to Microsoft SEAL version 4.1.
Users of previous versions of the library should look at the list of changes .
News
The BGV scheme is now available in Microsoft SEAL.
Implementation details are described in this paper .
We truly appreciate Alibaba Gemini Lab for making massive efforts to develop the BGV scheme and integrate it in Microsoft SEAL. And we would like to thank Privacy Technologies Research, Intel Labs, for continuous testing and reporting issues.
Starting from version 3.7.2, Microsoft SEAL will push new changes to the main , master , and contrib branches without creating a new version.
We adopt this approach to merge community contribution and resolve issues in a timely manner.
These branches will stay ahead of the latest version branch/tag.
New versions will be created when there are important bug fixes or new features.
The EVA compiler for CKKS is available at GitHub.com/Microsoft/EVA . See CKKS Programming with EVA below
... (truncated, 38 KB total)8a803827c20a0bd1 | Stable ID: sid_GnxKgPxoiJ