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 just moved one step closer to the engine room of real ML teams. The interesting part is not the crypto theater, it is the scikit-learn compatibility.
When encrypted inference fits existing workflows, one of the biggest excuses starts to disappear.
Sources
