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

111–120 of 305 posts

Re: Google is making private AI practical with homomorphic encryption

#111

Post by hellohello2 »

pinkmuffinere wrote: post #108
hellohello2 wrote: post #102

Earlier quoted context omitted.

The top comment mentions a ~10^3 overhead. Am I crazy (or already old?) for thinking this is not a very large constant?

Oh I see, you’re arguing that computer growth will make this more attractive. I think it’s a decent argument, although personally I find it unconvincing. More compute will be allocated between all the existing options, and I suspect it will go towards faster/better inference, instead of encryption. For most use cases people just don’t care much about encryption, and when feature prioritization comes around it always…

Yes, I think it really depends on the task. Clearly we won't be willing to spend 1000x on tokens for our everyday needs. But what about for the police monitoring conversations? I'd very much like my chats to stay encrypted, but there have been laws pushing against this. Technology like this provides a real solution i.e. you can scan chats for keywords without actually reading them, and get a warrant if you find something.

Re: Google is making private AI practical with homomorphic encryption

#113

Post by bhu8 »

clayhacks wrote: post #54
sabretooth1405 wrote: post #16

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.

Do you think that’s like a fundamental limit or something that will improve with time and new algorithms?

I wouldn't be very bullish.

Homomorphic encryption got significantly efficient with the first few iterations, but I don't really see the necessary orders of magnitude savings coming soon. You could reduce this by some partial encryption schemes (e.g., for LLMs you need a handful of basic operations) but a better alternative already exists: multi-party computation.

Source: I did research in this area in the past.

Re: Google is making private AI practical with homomorphic encryption

#114

Post by cantalopes »

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.

That doesn't protect their ad targeting in the eyes of regulators, so no point in turning that on by default

Re: Google is making private AI practical with homomorphic encryption

#115

Post by cantalopes »

It's a step to provide targeted advertising with mathematically provable "no sensitive info stored" approach. The google must fight really hard because this is the only source of income that makes sense for their position. And it /is/ quite evil tbh

Re: Google is making private AI practical with homomorphic encryption

#116

Post by PunchyHamster »

asdfman123 wrote: post #105
bevekspldnw wrote: post #56

Earlier quoted context omitted.

Commercially viable for Google boils down to can they attribute ads behaviors to it or not. Then there’s a second tier of things that just make those wheels turn and if they do or don’t make ads revenue is nominally immaterial. The teams doing this stuff at Google are purely for show, none of this makes it into any real products. There’s the narrow exception of stuff like gboard, that does use privacy preserving ML/f…

GCP exists, friend. Right now industries are locked out of AI tools due to privacy laws. If Google Cloud can offer FHE-powered tools, a hospital can run Google’s AI diagnostic models on encrypted brain scans without violating privacy laws. FHE effectively removes the primary regulatory barrier keeping enterprise customers off the cloud.

At that kind of amount of waste putting 2U server with some GPUs in hospital would be cheaper

Re: Google is making private AI practical with homomorphic encryption

#117

Post by hamper653 »

filup wrote: post #66
drdeca wrote: post #61

Earlier quoted context omitted.

Here’s a very simple one-time-pad style construction for homeomorphic (but not fully homeomorphic) encryption. Suppose the plaintext, ciphertext, and key, are each a natural number modulo 5. The key is selected uniformly at random. The ciphertext is obtained by adding the key to the plaintext (and as a result is also uniform random). Then the ciphertext is sent to the server. The server only has the ciphertext, which…

What does that have to do with incpa? I send this server a question encrypted. It stays encrypted yet the server distinguished my ciphertext enough to produce a coherent reply. That means there was enough information in the ciphertext for the server to perform the inference, even if it was obscured to where it looks indistinguishable, it apparently wasn't. This doesn't remove trust from the equation, it puts the trus…

> That means there was enough information in the ciphertext for the server to perform the inference

The server doesn’t need any information to perform inference.

Re: Google is making private AI practical with homomorphic encryption

#119

Post by asdfman123 »

PunchyHamster wrote: post #116
asdfman123 wrote: post #105

Earlier quoted context omitted.

GCP exists, friend. Right now industries are locked out of AI tools due to privacy laws. If Google Cloud can offer FHE-powered tools, a hospital can run Google’s AI diagnostic models on encrypted brain scans without violating privacy laws. FHE effectively removes the primary regulatory barrier keeping enterprise customers off the cloud.

At that kind of amount of waste putting 2U server with some GPUs in hospital would be cheaper

Making things 10x more expensive to reduce legal liability is what hospitals are all about

Re: Google is making private AI practical with homomorphic encryption

#120

Post by llleeeoooh »

siddthesquid wrote: post #106
Eueudhsbsj32 wrote: post #90

Earlier quoted context omitted.

Aren't there already much more efficient ways to make inference private? Using regular encryption and secure enclaves, there are already providers that are roughly 2x the cost of normal providers. For example, https://tinfoil.sh/

If I used regular encryption to send my credit card information to an AI with fraud detection, the provider still needs to decrypt that data on their side at some point before it goes into the AI. Using this other encryption, the provider has neither need nor capability to decrypt it on their end, so the user gets extra security.

this is not entirely true, I think. secure enclaves can provide guarantee such that even the host machine cannot inspect the contents within the VM. so even though the AI model itself needs to see plaintext, all is happening in the enclave which the provider cannot see.

the main difference is where the guarantee comes from. for FHE, it comes from math, which we trust. for secure enclave, the guarantee comes from Intel/AMD's promise that their hardware is bugless/backdoorless, and that your adversary cannot directly inspect bits in the hardware

Post reply on HN