[Resource Topic] 2023/257: Deep Neural Networks for Encrypted Inference with TFHE

Welcome to the resource topic for 2023/257

Title:
Deep Neural Networks for Encrypted Inference with TFHE

Authors: Andrei Stoian, Jordan Frery, Roman Bredehoft, Luis Montero, Celia Kherfallah, Benoit Chevallier-Mames

Abstract:

Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, Neural Networks are the dominant machine learning model for unstructured data.

In this work we show how to construct Deep Neural Networks (DNN) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits. We discuss the constraints and show the architecture of DNNs for two computer vision tasks. We benchmark the architectures using the Concrete stack, an open-source implementation of TFHE.

ePrint: https://eprint.iacr.org/2023/257

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .