Privacy-Enhanced Machine Learning with Functional Encryption

Tilen Marc; Miha Stopar; Jan Hartman; Manca Bizjak; Jolanda Modic

Paper 2019/1129

Privacy-Enhanced Machine Learning with Functional Encryption

Tilen Marc, Miha Stopar, Jan Hartman, Manca Bizjak, and Jolanda Modic

Abstract

Functional encryption is a generalization of public-key encryption in which possessing a secret functional key allows one to learn a function of what the ciphertext is encrypting. This paper introduces the first fully-fledged open source cryptographic libraries for functional encryption. It also presents how functional encryption can be used to build efficient privacy-enhanced machine learning models and it provides an implementation of three prediction services that can be applied on the encrypted data. Finally, the paper discusses the advantages and disadvantages of the alternative approach for building privacy-enhanced machine learning models by using homomorphic encryption.

Metadata

Available format(s): PDF
Category: Implementation
Publication info: Published elsewhere. Minor revision. ESORICS 2019
DOI: 10.1007/978-3-030-29959-0_1
Keywords: functional encryption machine learning
Contact author(s): tilen marc @ xlab si
History: 2019-10-02: received
Short URL: https://ia.cr/2019/1129
License: CC BY

BibTeX

@misc{cryptoeprint:2019/1129,
      author = {Tilen Marc and Miha Stopar and Jan Hartman and Manca Bizjak and Jolanda Modic},
      title = {Privacy-Enhanced Machine Learning with Functional Encryption},
      howpublished = {Cryptology ePrint Archive, Paper 2019/1129},
      year = {2019},
      doi = {10.1007/978-3-030-29959-0_1},
      note = {\url{https://eprint.iacr.org/2019/1129}},
      url = {https://eprint.iacr.org/2019/1129}
}