Spaces:
Running
on
CPU Upgrade
Try Concrete ML yourself (we're open source).
Concrete-ML is a Privacy-Preserving Machine Learning (PPML) open-source set of tools built on top of The Concrete Framework by Zama. It aims to simplify the use of fully homomorphic encryption (FHE) for data scientists to help them automatically turn machine learning models into their homomorphic equivalent. Concrete-ML was designed with ease-of-use in mind, so that data scientists can use it without knowledge of cryptography. Notably, the Concrete-ML model classes are similar to those in scikit-learn and it is also possible to convert PyTorch models to FHE.
We're open source, try it here: https://github.com/zama-ai/concrete-ml
Any question? Ask our team: https://community.zama.ai
Hey, great blog and space! I think a flow chart would be really helpful to explain the high level understanding :)
@derek-thomas Thanks for the kind words!
What do you have in mind about the flow chart?
Also, quick note, have you checked our bounty program at Zama? https://github.com/zama-ai/bounty-program - we reward contributors who submit ML tutorials, if you're interested to dig in our tech, check out if interested and let me know if any questions!
Cheers
- I think it would be good to show the flow of the steps and also when the data is encrypted and decrypted.
- Really interesting. Ill think about it!