Sensitive Tuning of Large Scale CNNs for E2E Secure Prediction using Homomorphic Encryption. (arXiv:2304.14836v1 [cs.LG])

Privacy-preserving machine learning solutions have recently gained
significant attention. One promising research trend is using Homomorphic
Encryption (HE), a method for performing computation over encrypted data. One
major challenge in this approach is training HE-friendly, encrypted or
unencrypted, deep CNNs with decent accuracy. We propose a novel training method
for HE-friendly models, and demonstrate it on fundamental and modern CNNs, such
as ResNet and ConvNeXt. After training, we evaluate our models by running
encrypted samples using HELayers SDK and proving …

accuracy attention challenge cnns computation data e2e encrypted encrypted data encryption homomorphic encryption large machine machine learning major performing prediction privacy research scale solutions training trend unencrypted