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

Machine Learning on Encrypted Data Without Decrypting It

juliacomputing.com

Post reply on HN
Print view View original

21–30 of 122 posts

Re: Machine Learning on Encrypted Data Without Decrypting It

#21

Post by ummonk »

peteradio wrote: post #11
KenoFischer wrote: post #4

Earlier quoted context omitted.

Just to clarify, homomorphic encryption does not expose patterns. At every point in the computation the ciphertexts are computationally indistinguishable from random. The result of evaluating the ML model will be an encrypted prediction that you then need to send back to whoever encrypted the data (or more precisely whoever has the key - doesn't need to be the same person) so they can decrypt and use the prediction.

That seems nontrivial that the same key would be used to decrypt the result. Does this only work for some subset of ML models?

The ML model has to use certain operations (which are homomorphic to the encryption) as its building blocks, but with fully homomorphic encryption you can put an arbitrary number of the building blocks together so you can build complex ML models out of those.

Re: Machine Learning on Encrypted Data Without Decrypting It

#22

Post by Stasis5001 »

As somebody with some ML background but no expertise in crypto, is the following ELI~20 summary correct?

We take an ML model trained on unencrypted data, use a 'homomorphic evaluation' technique (let's just leave that as magic here) to convert the model operation-by-operation to a model that runs on encrypted data, do a little more crypto magic, and we've solved the business problem described at the beginning of the article.

(In particular, if you train a model on encrypted data you get a really bad model, right?)

Re: Machine Learning on Encrypted Data Without Decrypting It

#23

Post by ummonk »

brenden2 wrote: post #19
LeanderK wrote: post #9

Earlier quoted context omitted.

Maybe i misunderstood something, but they are not really inferring information. The model is still encrypted, the outsider doesn't know what's going on. Wouldn't salt destroy the homomorphic property?

Homomorphic encryption is malleable[1] in that it can, with enough information, be decrypted without knowing the private keys in some cases. For example, if you can correlate with other data it may be possible to effectively undo the encryption. This is more like anonymization (effectively a one-way hash) than encryption. If you encrypt 2 different values with the same algorithm and key, you will get the same ciphert…

There is no reason to reuse the same key though...

Re: Machine Learning on Encrypted Data Without Decrypting It

#24

Post by yowlingcat »

ChrisRackauckas wrote: post #20

This blog post reminds me of the "Machine Learning Systems are Stuck in a Rut" paper [1], where they mentioned: > It is hard to experiment with front end features like named dimensions, because it is painful to match them to back ends that expect calls to monolithic kernels with fixed layout. On the other hand, there is little incentive to build high quality back ends that support other features, because all the fron…

Thanks for this provocative comment -- if you don't mind me asking, what do you think the tradeoffs are between using Julia and Python for ML in production? I get the idea of right tool for the right job and all, and I know that Python has a fantastic ecosystem. But, how close is Julia? How developed is the ecosystem right now, and how fast is it developing?

Re: Machine Learning on Encrypted Data Without Decrypting It

#25

Post by KenoFischer »

Stasis5001 wrote: post #22

As somebody with some ML background but no expertise in crypto, is the following ELI~20 summary correct? We take an ML model trained on unencrypted data, use a 'homomorphic evaluation' technique (let's just leave that as magic here) to convert the model operation-by-operation to a model that runs on encrypted data, do a little more crypto magic, and we've solved the business problem described at the beginning of the…

Yep, that's correct. With the minor caveat that we choose an ML model that's "easy" to evaluate using homomorphic encryption.

Re: Machine Learning on Encrypted Data Without Decrypting It

#27

Post by peteradio »

KenoFischer wrote: post #18
peteradio wrote: post #11

Earlier quoted context omitted.

That seems nontrivial that the same key would be used to decrypt the result. Does this only work for some subset of ML models?

I may be missing the question, so let me know if I do, but the point here is just that the crypto system is asymmetric. There's three kinds of keys, public, private and evaluation (as usual you can derive the others from the private key). Whoever has the public key can encrypt, whoever has the private key can decrypt and evaluation may or may not need the evaluation keys depending on what you're computing. As for whi…

Ok, I think you answered my question, basically I was missing the public key. So you send an encrypted picture of a cat to the encryption trained model and it returns an answer which is encrypted using the public key. (as a super simple example)

Re: Machine Learning on Encrypted Data Without Decrypting It

#28

Post by brenden2 »

ummonk wrote: post #23
brenden2 wrote: post #19

Earlier quoted context omitted.

Homomorphic encryption is malleable[1] in that it can, with enough information, be decrypted without knowing the private keys in some cases. For example, if you can correlate with other data it may be possible to effectively undo the encryption. This is more like anonymization (effectively a one-way hash) than encryption. If you encrypt 2 different values with the same algorithm and key, you will get the same ciphert…

There is no reason to reuse the same key though...

If you used a different key for each datum then you wouldn't be able to do this type of analyses.

This analyses depends on the property of the same values producing the same ciphertext, which also mean you're leaking information.

Re: Machine Learning on Encrypted Data Without Decrypting It

#30

Post by voxic11 »

marviel wrote: post #7
KenoFischer wrote: post #4

Earlier quoted context omitted.

Just to clarify, homomorphic encryption does not expose patterns. At every point in the computation the ciphertexts are computationally indistinguishable from random. The result of evaluating the ML model will be an encrypted prediction that you then need to send back to whoever encrypted the data (or more precisely whoever has the key - doesn't need to be the same person) so they can decrypt and use the prediction.

Do you have a reference somewhere that backs up your assertions, where I can read more on this topic? I'm super curious about it.

He is just stating the definition of homomorphic encryption. There are lots of papers on the topic. The one mentioned in the article is a good starting point. "Homomorphic Encryption for Arithmetic of Approximate Numbers" https://eprint.iacr.org/2016/421.pdf
Post reply on HN