concrete-ml
FHE ML framework
A framework for privacy-preserving machine learning using fully homomorphic encryption
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.
997 stars
21 watching
143 forks
Language: Python
last commit: 5 days ago
Linked from 2 awesome lists
data-sciencefhefully-homomorphic-encryptionhomomorphic-encryptionmachine-learningppmlprivacypythonscikit-learntfhetorch
ethicalml/awesome-production-machine-learning
jonaschn/awesome-heRelated projects:
| Repository | Description | Stars |
|---|---|---|
| zama-ai/concrete | A compiler that converts Python programs into homomorphic encryption algorithms | 1,248 |
| zama-ai/tfhe-rs | A library implementing homomorphic encryption and arithmetic over encrypted data | 947 |
| zama-ai/fhevm | An EVM-compatible smart contract library enabling fully homomorphic encryption for confidential transactions and state management | 407 |
 facebookresearch/crypten | A framework for applying secure computing techniques to machine learning models without modifying the underlying frameworks. | 1,539 |
 trustworthycomputing/t2-fhe-compiler-and-benchmarks | A framework providing a standardized benchmark suite and cross compiler for fully homomorphic encryption libraries | 32 |
 ai-secure/crfl | This project presents a framework for robust federated learning against backdoor attacks. | 71 |
 tf-encrypted/tf-encrypted | Enables secure machine learning computations in TensorFlow without requiring expertise in cryptography or distributed systems. | 1,210 |
 vernamlab/cufhe | A CUDA-accelerated Fully Homomorphic Encryption Library | 212 |
 openfheorg/openfhe-development | An open-source library for fully homomorphic encryption and secure multiparty computation | 765 |
 h2oai/article-information-2019 | A framework for building and evaluating machine learning systems with high accuracy and interpretability, particularly in human-centered applications. | 13 |
 kryptnostic/krypto | An implementation of multivariate quadratic fully homomorphic encryption in C++ | 50 |
 latticex-foundation/rosetta | Provides privacy-preserving solutions for artificial intelligence without requiring expertise in cryptography or trusted execution environments. | 566 |
 lducas/fhew | A C++ library implementing a fully homomorphic encryption scheme for secure evaluation of boolean circuits on encrypted data. | 221 |
| vernamlab/cuhe | A CUDA-accelerated library for homomorphic encryption and evaluation of polynomial rings. | 194 |
 mortendahl/tf-encrypted | A framework for training and prediction on encrypted data using secure multi-party computation and homomorphic encryption in TensorFlow. | 3 |