Authors: Morten Dahl,Jason Mancuso,Yann Dupis,Ben Decoste,Morgan Giraud,Ian Livingstone,Justin Patriquin,Gavin Uhma
ArXiv: 1810.08130
Document:
PDF
DOI
Artifact development version:
GitHub
Abstract URL: http://arxiv.org/abs/1810.08130v2
We present a framework for experimenting with secure multi-party computation
directly in TensorFlow. By doing so we benefit from several properties valuable
to both researchers and practitioners, including tight integration with
ordinary machine learning processes, existing optimizations for distributed
computation in TensorFlow, high-level abstractions for expressing complex
algorithms and protocols, and an expanded set of familiar tooling. We give an
open source implementation of a state-of-the-art protocol and report on
concrete benchmarks using typical models from private machine learning.