A Framework for Automatic Conversion of Neural Networks to Homomorphic Equivalents
This paper presents a framework that automatically converts a pre-trained Keras model into a CKKS equivalent, handling parameter inference, bootstrap placement and encrypted execution without retraining, with the user only providing a configuration of the encryption parameters.
Dennis van der Werff, Georgios Tasopoulos, Francesco Regazzoni
· Proceedings of the 14th Work... · 0 citations