Jeremy Here from Zama, if you are interested in learning more, check out our code on Github, everything we do is open source: https://github.com/zama-ai/fhevm
Zama's research on the application of Fully Homomorphic Encryption (FHE) to Large Language Models is now featured on @huggingface. Their Machine Learning team recently discovered that FHE has the potential to safeguard both user privacy and the Intellectual Property of the model.
Yes, you can find more information in this blog post, where we explain our choice to create a separate FHE library from our Concrete framework.
> https://www.zama.ai/post/announcing-tfhe-rs
Its main ambition is to show that FHE can be used for protecting data when using a Machine Learning model to predict outcomes without degrading its performance.
Disclaimer: I'm working at Zama (cited in the article posted).