Deep Neural Networks for Encrypted Inference with TFHE

Andrei Stoian, Jordan Frery, Roman Bredehoft, Luis Montero, Celia Kherfallah +1 more
2/13/2023
cs.LGcs.AIcs.CR

No official code found. Best implementation: zama-ai/concrete-ml (1,452 stars, last commit 2026-02-17).

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.

View on arXivView PDF

Code Implementations(1)

zama-ai/concrete-mlCommunity100%

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

1,452201Rust, ShellMar 23, 20228 months agoNOASSERTION
data-sciencefhefully-homomorphic-encryptionhomomorphic-encryptionmachine-learning+6 more

Similar Papers

ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping

86% match2025

Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference

85% match2025

High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts

82% match2023

HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx models

82% match2 repos202023

Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data

82% match2024

Privacy-Preserving 3-Layer Neural Network Training

82% match2023

Cite this paper

@article{stoian2023deep,
  title  = {Deep Neural Networks for Encrypted Inference with TFHE},
  author = {Andrei Stoian and Jordan Frery and Roman Bredehoft and Luis Montero and Celia Kherfallah and Benoit Chevallier-Mames},
  year   = {2023},
  eprint = {2302.10906},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.10906v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.10906.svg)](https://codeofpaper.com/paper/2302.10906)

Discussion