Machine Learning on Encrypted Data Without Decrypting It

Re:Machine Learning on Encrypted Data Without Decrypting It by rehasu on Tuesday November 26, 2019 @04:20PM (#21642826)

Think about what encryption should do. Think about what Machine Learning should do. The only thing you can do with ML on encrypted data is show where encryption needs to be improved. Or maybe there is a way to create ML models that produces output which only someone with the correct (private) key can understand.

[ Parent | on HN ]

Re:Machine Learning on Encrypted Data Without Decrypting It by KenoFischer on Tuesday November 26, 2019 @04:31PM (#21642956)

> Or maybe there is a way to create ML models that produces output which only someone with the correct (private) key can understand.

Yes, that's what the blog post describes how to do.

[ Parent | on HN ]

Re:Machine Learning on Encrypted Data Without Decrypting It by yati on Tuesday November 26, 2019 @04:35PM (#21642983)

> Nowhere was the user data decrypted and in particular the cloud provider does not have access to either the orignal image nor is it able to decrypt the prediction it computed.

That's from the post. Is that what you meant by creating a model whose results only the owner of the data can understand?

[ Parent | on HN ]

Re:Machine Learning on Encrypted Data Without Decrypting It by zionic on Tuesday November 26, 2019 @05:15PM (#21643308)

Precisely. Any encryption that allows an attacker to significantly reason about its underlying plaintext is broken.

[ Parent | on HN ]