Helen: Maliciously Secure Coopetitive Learning for Linear Models
release_go2j2nbfyjbx7d62wydrag5hmq
by
Wenting Zheng, Raluca Ada Popa, Joseph E. Gonzalez, Ion Stoica
2019
Abstract
Many organizations wish to collaboratively train machine learning models on
their combined datasets for a common benefit (e.g., better medical research, or
fraud detection). However, they often cannot share their plaintext datasets due
to privacy concerns and/or business competition. In this paper, we design and
build Helen, a system that allows multiple parties to train a linear model
without revealing their data, a setting we call coopetitive learning. Compared
to prior secure training systems, Helen protects against a much stronger
adversary who is malicious and can compromise m-1 out of m parties. Our
evaluation shows that Helen can achieve up to five orders of magnitude of
performance improvement when compared to training using an existing
state-of-the-art secure multi-party computation framework.
In text/plain
format
Archived Files and Locations
application/pdf 684.2 kB
file_eohetfnvrzh4piqjoklihdvj3y
|
arxiv.org (repository) web.archive.org (webarchive) |
1907.07212v2
access all versions, variants, and formats of this works (eg, pre-prints)