Google is making private AI practical with homomorphic encryption
1–10 of 305 posts
Re: Google is making private AI practical with homomorphic encryption
#2Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.
Re: Google is making private AI practical with homomorphic encryption
#3Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.
With Fully Homomorphic Encryption it's nobody elses.
The basic idea of of the project is to remove the need for trust.
Re: Google is making private AI practical with homomorphic encryption
#4Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.
With Fully Homomorphic Encryption it's nobody elses. The basic idea of of the project is to remove the need for trust.
It's google. They are good at engineering. Not at creating trust. After the bizillionth time they have broken trust, there is no need for benefit of the doubt.
Re: Google is making private AI practical with homomorphic encryption
#5Encryption or not, if it's on somebody else's server, it isn't yours. I don't believe Google has my best interest.
It's FHE for "cryptographically-secure private AI inference" not for every other service where they snoop into your behavioral information.
Re: Google is making private AI practical with homomorphic encryption
#6Does 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
Re: Google is making private AI practical with homomorphic encryption
#7Re: Google is making private AI practical with homomorphic encryption
#8Does 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
The linked project page [1] claims to be fully homomorphic. Assuming the claim holds (I haven't verified it), then there is provably no way for Google or anyone else to obtain any information from the encrypted data or computation performed on them.
FHE is traditionally horrifically slow, so it's hard to imagine running anything beyond toy models with it. They list some applications on the original article page, but (presumably) they must be dramatically stripped down in order to run within any reasonable time budget. This is not going to run anything like a Sol/Opus any time soon.
[1]: https://heir.dev/
Re: Google is making private AI practical with homomorphic encryption
#9One 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).
Re: Google is making private AI practical with homomorphic encryption
#10It 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.