Counting 3,663 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1


HE Transformer for nGraph

The Intel® HE transformer for nGraph™ is a Homomorphic Encryption (HE) backend to the Intel® nGraph Compiler, Intel's graph compiler for Artificial Neural Networks.

Homomorphic encryption is a form of encryption that allows computation on encrypted data, and is an attractive remedy to increasing concerns about data privacy in the field of machine learning. For more information, see our paper.

This project is meant as a proof-of-concept to demonstrate the feasibility of HE on local machines. The goal is to measure performance of various HE schemes for deep learning. This is not intended to be a production-ready product, but rather a research tool.

Currently, we support two encryption schemes, implemented by the Simple Encrypted Arithmetic Library (SEAL) from Microsoft Research:

Additionally, we integrate with the Intel® nGraph™ Compiler and runtime engine for TensorFlow to allow users to run inference on trained neural networks through Tensorflow.


The examples directory contains a deep learning example which depends on the Intel® nGraph™ Compiler and runtime engine for TensorFlow.

Building HE Transformer


  • We currently only support Ubuntu 16.04
  • CMake >= 3.10, although different versions may work
  • GCC version 7, although different versions may work
  • OpenMP is strongly suggested, though not strictly necessary. You may experience slow runtimes without OpenMP
  • python3.5 and pip3
  • virtualenv v16.1.0
  • bazel v0.16.0

The following dependencies are built automatically

To install bazel

 chmod +x
 ./ --user

Make sure to add and source the bin path to your ~/.bashrc file in order to be able to call bazel from the user's installation we set up:

 export PATH=$PATH:~/bin
 source ~/.bashrc

1. Build HE-Transformer

Before building, make sure you deactivate any active virtual environments (i.e. run deactivate)

git clone
cd he-transformer
export HE_TRANSFORMER=$(pwd)
mkdir build
make -j install
source external/venv-tf-py3/bin/activate

The first build will compile Tensorflow and the ng-tf bridge. To speed up subsequent builds, you can avoid compiling Tensorflow and ng-tf bridge by calling


2. Run C++ unit-tests

Ensure the virtual environment is active, i.e. run source $HE_TRANSFORMER/external/venv-tf-py3/bin/activate

# To run CKKS unit-test
./test/unit-test --gtest_filter="HE_SEAL_CKKS.*abc*"
# To run BFV unit-test
./test/unit-test --gtest_filter="HE_SEAL_BFV.*abc*"
# To run all C++ unit-tests

3. Run Simple python example

Ensure the virtual environment is active, i.e. run source $HE_TRANSFORMER/external/venv-tf-py3/bin/activate

cd $HE_TRANSFORMER/examples
# Run with CPU
# To run CKKS unit-test
# To run BFV unit-test

For a deep learning example, see examples/cryptonets/.

Code formatting

Please run maint/ before submitting a pull request.

Latest Releases
Release v0.4.0-rc0
 Mar. 15 2019
 Mar. 15 2019
Release v0.3.0
 Mar. 4 2019
Release v0.3.0-rc1
 Jan. 30 2019
Benchmarks for results replication
 Jan. 18 2019