cipherflow-fhe/latti-ai

A framework for performing AI model inference on encrypted data.

26
/ 100
Experimental

This platform helps AI developers deploy machine learning models that can process sensitive user data while keeping it encrypted. It takes a standard AI model (like a PyTorch or ONNX file) and automatically converts it into a privacy-preserving inference service. The output is an encrypted AI model ready for deployment, ensuring neither the server nor the user can see the raw data or model details.

Use this if you are an AI developer who needs to run your machine learning models on highly sensitive data (e.g., medical records, financial information) without ever decrypting it on the server.

Not ideal if your AI application does not involve sensitive data requiring end-to-end encryption or if you need to frequently inspect intermediate model results in plaintext.

privacy-preserving AI encrypted machine learning secure data processing AI model deployment homomorphic encryption
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

C++

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cipherflow-fhe/latti-ai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.