Cryptology ePrint Archive: Report 2021/091

Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks

Ilaria Chillotti and 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.

Category / Keywords: applications / privacy; homomorphic encryption; machine learning; inference

Date: received 25 Jan 2021

Contact author: marc joye at zama ai

Available format(s): PDF | BibTeX Citation

Version: 20210127:133406 (All versions of this report)

Short URL: ia.cr/2021/091


[ Cryptology ePrint archive ]