Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google is making private AI practical with homomorphic encryption

blog.google

Post reply on HN
Print view View original

31–40 of 305 posts

Re: Google is making private AI practical with homomorphic encryption

#31

Post by bmenrigh »

Has FHE really progressed so far that it's now so efficient that doing computation on an encrypted prompt is feasible? I thought even basic operations like FHE addition were still thousands of times more complex. The only mention in the article I see is:

> But while homomorphic encryption has a nontrivial cost overhead, it shifts the capability/privacy trade-off to a question of cost. And the cost of homomorphic encryption is rapidly decreasing.

Which doesn't spell out exactly hon "nontrivial" the cost overhead still is.

Re: Google is making private AI practical with homomorphic encryption

#32

Post by filup »

drdeca wrote: post #20
filup wrote: post #15

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.

Eh? With secret sharing one can do computation on a shared secret where it is provable that no individual party can recover any information about the data with their share alone. I don’t see why you conclude that FHE couldn’t be close to as secure as that. (Like, not information theoretically, but with computationally bounded adversaries.)

I'm not saying that you can't design a system for secure cloud computing.

Re: Google is making private AI practical with homomorphic encryption

#33

Post by flambo »

filup wrote: post #15

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.

This is actually the magic of FHE. The ciphertext is indistinguishable from noise AND can be computed on, it just looks like different noise.

If you believe the underlying cryptographic hardness assumption of LWE/RLWE/etc, then yes Google cannot see any of the input or output of the model.

Re: Google is making private AI practical with homomorphic encryption

#35

Post by NyxWulf »

Maybe I'm not understanding this, but how is it that you can know enough about the data to process it without undermining the fundamental concept of encryption? Isn't encrypted data supposed to be just random noise without the key? The more you know about the underlying data the easier it gets to decrypt? Does this mean someone can just steal your encrypted data and use that to steal your identity without even needing to decrypt it anymore?

Re: Google is making private AI practical with homomorphic encryption

#36

Post by drdeca »

filup wrote: post #32
drdeca wrote: post #20

Earlier quoted context omitted.

Eh? With secret sharing one can do computation on a shared secret where it is provable that no individual party can recover any information about the data with their share alone. I don’t see why you conclude that FHE couldn’t be close to as secure as that. (Like, not information theoretically, but with computationally bounded adversaries.)

I'm not saying that you can't design a system for secure cloud computing.

You said that FHE is an oxymoron, seemingly on the basis that in proper encryption the ciphertext is indistinguishable from noise, and you think this can’t be true of FHE. I am arguing to the contrary.

In the secret sharing multi-party computation schemes, the individual shares of the secret are random and have no information about the plaintext.

I see no reason that FHE can’t have ciphertexts indistinguishable from noise.

Re: Google is making private AI practical with homomorphic encryption

#37

Post by sheesdev »

I've published two papers on using HE for ML and it's nice, but also alarming, to see big players like Google and Microsoft making decent tools for performing HE. Although the technology is still much farther out from being commercially viable, it does pose an interesting problem about how these data aggregation companies will utilise a tech that is inherently private.

Re: Google is making private AI practical with homomorphic encryption

#38

Post by drdeca »

LoganDark wrote: post #24
noman-land wrote: post #19

Earlier quoted context omitted.

100% not an expert but my understanding was that part of what you are proving by signing the computation is that the computation itself was performed specifically as agreed to. I may be mixing this up with zero knowledge proofs.

If this were the case it would be necessary to send the entire model weights in response to every request which would be a bit inconvenient.

Hmm, could one instead of sending the model weights, send like, a merkle tree root for them, not exactly specifying the model, but at least demonstrating that the same model is used each time?

Re: Google is making private AI practical with homomorphic encryption

#39

Post by rexpop »

amazingamazing wrote: post #26
Cider9986 wrote: post #22

This is the same Google that doesn't have e2ee on their password manager by default. Like WTF, it's a password manager.

If you think about it for a moment you will realize the average user does not want that.

I suspect that your one moment of thought follows many years of contemplation. Maybe you can fill us in on some of that background.

Re: Google is making private AI practical with homomorphic encryption

#40

Post by amazingamazing »

rexpop wrote: post #39
amazingamazing wrote: post #26

Earlier quoted context omitted.

If you think about it for a moment you will realize the average user does not want that.

I suspect that your one moment of thought follows many years of contemplation. Maybe you can fill us in on some of that background.

How do you make e2e password management work on multiple devices as convenient as not? You cannot.

Most people who use Google trust them. And if you do not trust them then why are you using their password manager? You see? Hence why they do not bother.

Of course one might read this and say, multi device e2ee is possible! Sure, but can you allow for recovery when people inevitably lose their recovery codes at scale? If you really care about this it is not necessary to go with Google.

I stand by my original comment:

The average user does not want it.

Post reply on HN