End-to-end encrypted ML inference with Amazon SageMaker AI and FHE
TL;DR
This blog has previously discussed FHE for ML inference in the post Enable fully homomorphic encryption with Amazon SageMaker endpoints for secure, real-time inferencing, but this post goes a little further. That previous post showed how to implement FHE-based inference 'from scratch' by hand-crafting a linear-regression algorithm using a low-level library called SEAL.
Nauti's Take
FHE is moving out of the crypto display case and into the tooling of real ML teams. Performance is still the hard part, but concrete-ml lowers the barrier fast.
If your privacy strategy is mostly policy paperwork, this removes one more comfortable excuse.
Sources
