Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

Curl: Private LLMs through Wavelet-Encoded Look-Up Tables

Samples of multi-class text classification with Differential Privacy Tensorflow 2.0

Sisyphus: A Cautionary Tale of Using Polynomial Activations in Privacy-Preserving Deep Learning

Hands-on part of the Federated Learning and Privacy-Preserving ML tutorial given at VISUM 2022