microsoft/robustdg

Toolkit for building machine learning models that generalize to unseen domains and are robust to privacy and other attacks.

44
/ 100
Emerging

This toolkit helps machine learning researchers build and evaluate models that perform reliably even when exposed to new, unseen data environments or when facing privacy and other security threats. It takes your machine learning model and training data, and outputs performance metrics related to how well your model generalizes and resists attacks. It's designed for machine learning scientists and researchers focused on model robustness and generalization.

175 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner needing to develop and test models that remain accurate and secure when deployed in diverse, unpredictable real-world scenarios or against adversarial actions.

Not ideal if you are looking for a pre-built, ready-to-deploy machine learning solution rather than a research toolkit for model development and evaluation.

machine-learning-research model-robustness domain-generalization adversarial-robustness privacy-preserving-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

175

Forks

29

Language

Python

License

MIT

Last pushed

Oct 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/robustdg"

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