Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks

Ilaria Chillotti; Marc Joye; Pascal Paillier

Paper 2021/091

Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks

Ilaria Chillotti, Marc Joye, and Pascal Paillier

Abstract

In many cases, machine learning and privacy are perceived to be at odds. Privacy concerns are especially relevant when the involved data are sensitive. This paper deals with the privacy-preserving inference of deep neural networks. We report on first experiments with a new library implementing a variant of the TFHE fully homomorphic encryption scheme. The underlying key technology is the programmable bootstrapping. It enables the homomorphic evaluation of any function of a ciphertext, with a controlled level of noise. Our results indicate for the first time that deep neural networks are now within the reach of fully homomorphic encryption. Importantly, in contrast to prior works, our framework does not necessitate re-training the model.

Metadata

Available format(s): PDF
Category: Applications
Publication info: Published elsewhere. CSCML 2021
DOI: 10.1007/978-3-030-78086-9_1
Keywords: privacy homomorphic encryption machine learning inference
Contact author(s): marc joye @ zama ai
History: 2021-11-25: revised; 2021-01-27: received; See all versions
Short URL: https://ia.cr/2021/091
License: CC BY

BibTeX

@misc{cryptoeprint:2021/091,
      author = {Ilaria Chillotti and Marc Joye and Pascal Paillier},
      title = {Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks},
      howpublished = {Cryptology {ePrint} Archive, Paper 2021/091},
      year = {2021},
      doi = {10.1007/978-3-030-78086-9_1},
      url = {https://eprint.iacr.org/2021/091}
}