Paper 2017/762

Private Collaborative Neural Network Learning

Melissa Chase, Ran Gilad-Bachrach, Kim Laine, Kristin Lauter, and Peter Rindal

Abstract

Machine learning algorithms, such as neural networks, create better predictive models when having access to larger datasets. In many domains, such as medicine and finance, each institute has only access to limited amounts of data, and creating larger datasets typically requires collaboration. However, there are privacy related constraints on these collaborations for legal, ethical, and competitive reasons. In this work, we present a feasible protocol for learning neural networks in a collaborative way while preserving the privacy of each record. This is achieved by combining Differential Privacy and Secure Multi-Party Computation with Machine Learning.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Preprint. MINOR revision.
Keywords
deep learningneural networksdifferential privacysecure multi-party computation
Contact author(s)
kim laine @ microsoft com
History
2017-08-08: received
Short URL
https://ia.cr/2017/762
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2017/762,
      author = {Melissa Chase and Ran Gilad-Bachrach and Kim Laine and Kristin Lauter and Peter Rindal},
      title = {Private Collaborative Neural Network Learning},
      howpublished = {Cryptology ePrint Archive, Paper 2017/762},
      year = {2017},
      note = {\url{https://eprint.iacr.org/2017/762}},
      url = {https://eprint.iacr.org/2017/762}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.