Re:Machine Learning on Encrypted Data Without Decrypting It
by ummonk on Tuesday November 26, 2019 @05:34PM
(#21643459)
It is really straightforward. The currently top voted comment basically explains it. If you take data x and encrypt it with encryption function C to get C(x), and then apply your machine learning model f to that to get f(C(x)), homomorphism means that f(C(x)) = C(f(x)) (because f and C commute), so the client can then apply the decryption to the result to get C-1(f(C(x)) = C-1(C(f(x)) = f(x).
Re:Machine Learning on Encrypted Data Without Decrypting It
by xvector on Tuesday November 26, 2019 @07:25PM
(#21644166)
You might want to clarify that “C-1” is actually C^-1 because otherwise I was wondering where subtraction comes into play.
Re:Machine Learning on Encrypted Data Without Decrypting It
by ummonk on Tuesday November 26, 2019 @11:37PM
(#21645285)
Whoops, too late to edit; thanks for posting the clarification.
Re:Machine Learning on Encrypted Data Without Decrypting It
by ct520 on Tuesday November 26, 2019 @07:14PM
(#21644093)
more like really straight forward over my head. I appreciate you taking the time to explain it - still can't grasp the concept. Back to framework connecting.
Re:Machine Learning on Encrypted Data Without Decrypting It
by mikorym on Wednesday November 27, 2019 @12:29AM
(#21645502)
But are you saying that a ML model is just a function? The function C is clear, but what is f?
What is the domain and what is the codomain? If f and C commute, then x in X is just your "data" and both the domain and codomain.
Edit:
> the top voted comment
Ah, I see that the top comment says that you use a pre-trained model. Intuitively that I think makes sense. Bot how about training the model itself?
Intuitively it may or may not make sense to people, but a proof would also clarify whether there are any caveats, limitations or other particuliarities.