Training on encrypted data


I’m confused. Is it possible to train on encrypted data?
I’m only seeing things about inference.

Hello Vanessa,

Indeed, we train only on non-encrypted data. Currently, Concrete ML is mainly to protect the privacy of inferences. To handle training on protected data, there are more adapted other technologies than FHE (differential privacy, multi party computation).

1 Like

Do you plan to develop something to training on protected data using FHE in the future? Would that intrinsically give bad results?
Can you explain the main problem about it?

We never know what we’ll do in the future, but I guess training on encrypted data is not the first priority of Zama. It could be very slow and with the 8b of precision, this would not be easy. We have advanced research projects to look at the subject.

1 Like