I'm interested in the two following processes:
Perform deep learning on homomorphic encrypted data
Perform deep learning predictions with a homomorphic encrypted model on unencrypted data. By this, I mean encrypting weights of a deep learning model, sending them to the data owner, and performing an encrypted prediction. The owner of the data will return me the encrypted prediction. See, for instance, this blog post for an example with logistic regression. I'm wondering if it's possible to do deep learning (with many hidden layers) with PHE (partially homomorphic encryption, e.g., Paillier) or if I need a FHE (fully homomorphic encryption).
References are welcome!