microsoft/private-benchmarking

A platform that enables users to perform private benchmarking of machine learning models. The platform facilitates the evaluation of models based on different trust levels between the model owners and the dataset owners.

32
/ 100
Emerging

This platform helps researchers and organizations evaluate machine learning models against datasets without either party fully revealing their proprietary model or sensitive data. It takes in a model from a 'Model Owner' and a dataset from a 'Dataset Owner', then produces performance benchmarks. This is for AI/ML researchers or data scientists who need to compare model performance under strict privacy constraints.

No commits in the last 6 months.

Use this if you need to benchmark the performance of an AI/ML model using a dataset that cannot be fully shared with the model owner, or vice versa, due to privacy or proprietary concerns.

Not ideal if you are looking for a production-ready system to regularly benchmark models, as this is an academic prototype and not yet hardened for real-world deployment.

machine-learning-evaluation privacy-preserving-ai model-benchmarking secure-computation large-language-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

MIT

Last pushed

Sep 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mlops/microsoft/private-benchmarking"

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