HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data. (arXiv:2011.01805v3 [cs.CR] UPDATED)

Privacy-preserving solutions enable companies to offload confidential data to
third-party services while fulfilling their government regulations. To
accomplish this, they leverage various cryptographic techniques such as
Homomorphic Encryption (HE), which allows performing computation on encrypted
data. Most HE schemes work in a SIMD fashion, and the data packing method can
dramatically affect the running time and memory costs. Finding a packing method
that leads to an optimal performant implementation is a hard task.

We present a simple and intuitive framework …

companies computation confidential data enable encrypted encrypted data encryption fashion framework government homomorphic encryption large networks neural networks party performing privacy regulations services solutions techniques third third-party tile work