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

201–210 of 305 posts

Re: Google is making private AI practical with homomorphic encryption

#201

Post by dhx »

odo1242 wrote: post #134
dhx wrote: post #63

Earlier quoted context omitted.

To throw out some real and up-to-date numbers from [1] for FHE at "128-bit security level", to sort 8x 8-bit unsigned integers on the most ordinary of desktop PCs, wait 3 seconds for the result. Want to sort 32x 8-bit unsigned integers instead? Come back 34 seconds later for the result. update: also see [2] for some primitive unsigned 64-bit integer operation benchmarks with the TFHE-rs library (winner in the sorting…

It’s slightly better for LLMs because FHE is really bad at branches (it ends up essentially having to try both branches), making sorts nearly the worst possible thing to try since it’s all branches. In the case of AI most things are just addition and multiplication which can make some things faster since there aren’t as many branches. But we’re still nowhere near viability.

I found [1] which appears to offer state-of-the-art performance of ~1000s latency for a FHE GPT-2 transformer block, equating I think to 3.33h inter-token latency (0.00008 token/s) for GPT-2(small) which has 12 transformer blocks. This result is using optimised packed arithmetic operations on a GPU as well--so seemingly is unlikely to have much performance upside from further optimisation.

I'm not sure I've interpreted [1] correctly though, and would appreciate correction if necessary.

[1] https://arxiv.org/pdf/2604.04783 -- GPU Acceleration of TFHE-Based High-Precision Nonlinear Layers for Encrypted LLM Inference -- Guoci Chen, Xiurui Pan, Qiao Li, Bo Mao, Congming Gao, Chengying Huan, Mingzhe Zhang, Jie Zhang -- Apr 2026

Re: Google is making private AI practical with homomorphic encryption

#202

Post by oofbey »

fedpost wrote: post #200
never_inline wrote: post #188

I think you folks are reading too much into it. I think the people working on FHE need to publish an AI-oriented pitch to retain funding from AI-pilled execs. Must be the same case with the golang post few days ago.

Yeah I don't think they actually want this. There's far too much deeply personal and useful data being freely feed to the companies running these models. People are giving them everything . Their thoughts, feelings, intentions, company IP... It's a fucking gold mine. There's just too much value in retraining on that data and even if there wasn't, the feds lean so heavily on Google search histories to get convictions…

All true. HE will never be used for anything real because it’s way to slow and inefficient, meaning you can only run the stupidest models on it. And there’s no commercial incentive to make it work because collecting data is too valuable.

But at the same time HE is classic Google promotion fodder. Really difficult technical problem! That’s what gets people promoted at Google. Nobody actually cares about it or will use it? That also is what gets people promoted at Google. Because Google only employs “the smartest people on earth” which means people who solve difficult problems. Difficult problems - not problems that need solving.

Re: Google is making private AI practical with homomorphic encryption

#203

Post by oofbey »

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.

Former Googler here. E2EE is easy. Nobody gets promoted at Google for solving easy problems. In fact if you set out to solve an easy problem, it looks bad at performance review time.

Re: Google is making private AI practical with homomorphic encryption

#204

Post by tomhow »

not_a_bot_4sho wrote: post #197
tomhow wrote: post #127

Earlier quoted context omitted.

> This is generally the test of extreme stupidity because those so adept rarely realize there is even a contradiction because they lack in critical thinking. > You can separate Cook is a garbage person We've banned this account. We've asked you politely, several times over the years to observe the guidelines. In recent times you've been acting more than ever like they don't apply to you. They do apply to you just as…

I wholeheartedly support moderation to keep a healthy community but this is asinine. My takeaway is that you were personally offended by the (mild) attack on Cook and Apple products, likely because you use them and associate them with your self worth, and responded in defense of ego. I say this based on observing casual usage of 'fool' and 'idiot' and other terms a myriad of times in other threads with no action or r…

Please don’t imagine my “true” motivation or inner psychological state and attack me for it. You have no idea what devices I use or what I think of Tim Cook. Even if I had any personal affection for him, if I banned accounts just for criticizing a product or individual I personally liked, I would not have lasted more than a few days before being hounded out by top users of the site.

It’s true that this comment alone was not sufficient for a ban; as I explained in my comment, it’s the pattern of comments, particularly in recent days, continuing a pattern over years that we’ve posted several warnings about. And it's the fact that other users who have a solid track record of contributing positively to HN are being driven away by that style of rhetoric from this user, or at least signaling that these comments were beyond the pale.

Our role here is to make HN a place where reasonable people feel they can have intellectually gratifying discussions that are of higher quality than elsewhere online. When we see signs that good contributors are being driven away by an escalating pattern of toxic comments from a user who has been warned many times over a decade, it would be negligent of us not to act.

As we say all the time, we don’t see every guidelines breach, or reply every time we do; there are over 10,000 comments posted each day and only two of us. But when we see an ongoing pattern of abuse, we always issue warnings, then ban the account if it continues. You’re always welcome to email us (hn@ycombinator.com) when you see anything egregious, or at least just flag the comment. That's what people do when they wholeheartedly support moderation.

Re: Google is making private AI practical with homomorphic encryption

#206

Post by r3trohack3r »

Does this also solve provable compute as a side effect? Since the compute is fully encrypted end-to-end, the host wouldn’t be able to modify the program and still give valid results?

So a caller could run a program on untrusted hardware and trust that the hardware actually ran the program?

Re: Google is making private AI practical with homomorphic encryption

#208

Post by LoganDark »

drdeca wrote: post #38
LoganDark wrote: post #24

Earlier quoted context omitted.

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?

I feel like that'd have to be generated as a side effect of the computation somehow?

Re: Google is making private AI practical with homomorphic encryption

#209

Post by froh »

pamcake wrote: post #107
froh wrote: post #86

Earlier quoted context omitted.

where does this factor "1000x" come from? I have doubts.

Most likely from above in thread. There is no reason to believe it should be lower than that - or even that low. Or do you have access to research claiming such achievements?

maybe I simply don't know how this works ;-)

I was very much surprised and asked. give me demerits for the way of asking.

but the question stays: how come an encryption scheme inflates data by this order of magnitude and needs GB sized keys?

where can I learn about this? not the nutty gritty details proofs and all but an overview. assume I did my CS masters in the 1990s and worked as SW eng ever since.

NVM, I asked Gemini

https://share.google/aimode/pqZO1VF3cGTeetamq

Post reply on HN