Neural Network Quantisation for Faster Homomorphic Encryption. (arXiv:2304.09490v1 [cs.CR])

Homomorphic encryption (HE) enables calculating on encrypted data, which
makes it possible to perform privacypreserving neural network inference. One
disadvantage of this technique is that it is several orders of magnitudes
slower than calculation on unencrypted data. Neural networks are commonly
trained using floating-point, while most homomorphic encryption libraries
calculate on integers, thus requiring a quantisation of the neural network. A
straightforward approach would be to quantise to large integer sizes (e.g. 32
bit) to avoid large quantisation errors. In …

data encrypted encrypted data encryption errors homomorphic encryption integer large network networks neural network neural networks point unencrypted unencrypted data work