Only 1000x overhead would make some image classification tasks go from 1ms to 1s. That’s viable for some applications!
Exactly. That is what we have today at Belfort; not enough for making all AI work privacy preserving, but fast enough for many applications, where otherwise unencrypted compute is not acceptable.
alt Hacker News
Exactly. That is what we have today at Belfort; not enough for making all AI work privacy preserving, but fast enough for many applications, where otherwise unencrypted compute is not acceptable.