Machine Learning on Encrypted Data Without Decrypting It

Post by madrafi » Wed, Nov 27, 2019, 3:51 PM UTC

k__ wrote: post #118

StefanKarpinski wrote: post #104

Earlier quoted context omitted.

Yes, it’s rather surprising that it can be done at all. And no, you train the model normally and then express the application of the model in terms of the set of primitive operations that the encryption scheme supports. Broadening the set of operations supported by the encryption scheme is an active area of research since having a better “instruction set” allows more computations to be done efficiently. It is also po…

Does this has something to do with all the operations being linear?

Not really ! Activation functions are usually non-linear. What happens is we turn our numbers into their counterparts in another group (abstract group) and work there (at a high-level).

Post by madrafi » Wed, Nov 27, 2019, 3:55 PM UTC

thefifthsetpin wrote: post #67

falcolas wrote: post #65

Earlier quoted context omitted.

So, you're training a statistical model - teaching it to recognize certain patterns - on data that is somehow wholly without patterns? Even with a certain amount of noise in the individual data points, if you're given enough data to train a statistical model to identify traits in the ciphertext you also probably have enough data to break the encryption. Also, something can be statistically random and still have patte…

> homomorphic encryption has not been broadly accepted as an allowed standard. I get that a lack of broad acceptance is a hard thing to source, but do you have one?

Last year a group of companies and institutions created a working standard. https://homomorphicencryption.org/standard/

Re: Machine Learning on Encrypted Data Without Decrypting It

Re: Machine Learning on Encrypted Data Without Decrypting It