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.
@article{arxiv.1810.08130,
title = {Private Machine Learning in TensorFlow using Secure Computation},
author = {Morten Dahl and Jason Mancuso and Yann Dupis and Ben Decoste and Morgan Giraud and Ian Livingstone and Justin Patriquin and Gavin Uhma},
journal= {arXiv preprint arXiv:1810.08130},
year = {2018}
}