zama-ai/concrete-ml
Privacy-preserving machine learning framework using fully homomorphic encryption, with scikit-learn and PyTorch API bindings.
Not currently ranked — collecting fresh signals.
star history
Concrete ML is an open-source Python framework built on Zama’s Concrete FHE stack that allows data scientists to run machine learning models on encrypted data without requiring knowledge of cryptography. It provides model classes similar to scikit-learn that can perform inference and training over encrypted inputs. The framework integrates with traditional ML libraries and enables privacy-preserving predictions where data remains encrypted throughout computation.
Frequently asked
- What is zama-ai/concrete-ml?
- Privacy-preserving machine learning framework using fully homomorphic encryption, with scikit-learn and PyTorch API bindings.
- Is concrete-ml open source?
- Yes — zama-ai/concrete-ml is an open-source project tracked on heatdrop.
- What language is concrete-ml written in?
- zama-ai/concrete-ml is primarily written in Python.
- How popular is concrete-ml?
- zama-ai/concrete-ml has 1.4k stars on GitHub.
- Where can I find concrete-ml?
- zama-ai/concrete-ml is on GitHub at https://github.com/zama-ai/concrete-ml.