Efficient privacy-preserving inference for convolutional neural networks. (arXiv:2110.08321v2 [cs.LG] UPDATED)

The processing of sensitive user data using deep learning models is an area
that has gained recent traction. Existing work has leveraged homomorphic
encryption (HE) schemes to enable computation on encrypted data. An early work
was CryptoNets, which takes 250 seconds for one MNIST inference. The main
limitation of such approaches is that of the expensive FFT-like operations
required to perform operations on HE-encrypted ciphertext. Others have proposed
the use of model pruning and efficient data representations to reduce the …

arxiv convolutional neural networks inference lg networks neural networks privacy