Google is making private AI practical with homomorphic encryption

blog.google

33 points by u1hcw9nx an hour ago


sabretooth1405 - 5 minutes ago

My master's thesis is on a topic in this field (Privacy Preserving ML) and from my understanding HE and other techniques have very high overheads(~10^3) on inference tasks and thus aren't very commercially viable.

Cider9986 - a few seconds ago

[delayed]

filup - 7 minutes ago

Proper encryption means the ciphertext is indistinguishable from noise. So...in order to be able to process on it, you have to make it not indistinguishable from noise.

So I take offense to the term FHE. It's a oxymoron.

The whole thing immidiatly stands out as a sham to build trust where it's gone.

Deukhoofd - 16 minutes ago

It sounds neat, but I do wonder how viable this is commercially. How high do we rate the chances that governments around the world will step in before another kind of E2E is rolled out.

LoganDark - 17 minutes ago

One flaw with FHE is that it guarantees only that you need the key to see the inputs or outputs of the computation, but not necessarily that the computation is the one you want. For example, the computation could be adversarial for certain inputs, or an adversary could insert their own computation first (or last).

noident - 32 minutes ago

Does this rely on the Trust Me Bro model, or is there some way for the client to verify that the provider actually isn't able to see your inputs?

I want to read a whitepaper but all I can find is the tl;dw conference presentation

FloatArtifact - an hour ago

Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.