Desilo/liberate-fhe
A Fully Homomorphic Encryption (FHE) library for bridging the gap between theory and practice with a focus on performance and accuracy.
This library enables software developers to build applications that perform computations on encrypted data without ever decrypting it, ensuring privacy. It takes in sensitive numerical data and allows operations like addition and multiplication, outputting encrypted results that can later be securely decrypted. This is primarily for engineers and researchers creating privacy-preserving AI or data analysis systems.
138 stars. Available on PyPI.
Use this if you are a developer building privacy-preserving applications where computations need to occur on encrypted numerical data, especially in AI or machine learning contexts.
Not ideal if you need a solution for secure data sharing or privacy-preserving computations where the data is not numerical or the operations are not arithmetic.
Stars
138
Forks
18
Language
Python
License
BSD-3-Clause-Clear
Category
Last pushed
Nov 04, 2025
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Desilo/liberate-fhe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
flwrlabs/flower
Flower: A Friendly Federated AI Framework
JonasGeiping/breaching
Breaching privacy in federated learning scenarios for vision and text
zama-ai/concrete-ml
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on...
anupamkliv/FedERA
FedERA is a modular and fully customizable open-source FL framework, aiming to address these...
p2pfl/p2pfl
P2PFL is a decentralized federated learning library that enables federated learning on...