jopasserat / he-transformer

nGraph-HE: Deep learning with Homomorphic Encryption (HE) through Intel nGraph

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

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 the CKKS encryption scheme, 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.

Examples

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

Building HE Transformer

Dependencies

  • 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 v0.21.0

The following dependencies are built automatically

To install bazel

 wget https://github.com/bazelbuild/bazel/releases/download/0.21.0/bazel-0.21.0-installer-linux-x86_64.sh
 chmod +x bazel-0.21.0-installer-linux-x86_64.sh
 ./bazel-0.21.0-installer-linux-x86_64.sh --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 https://github.com/NervanaSystems/he-transformer.git
cd he-transformer
export HE_TRANSFORMER=$(pwd)
mkdir build
cd $HE_TRANSFORMER/build
cmake .. [-DCMAKE_CXX_COMPILER=g++-7 -DCMAKE_C_COMPILER=gcc-7]
make install
source external/venv-tf-py3/bin/activate

where [ ] indicate optional arguments.

The first build will compile Tensorflow. To speed up subsequent builds, you can avoid compiling Tensorflow by calling

cmake .. -DUSE_PREBUILT_TF=ON [-DCMAKE_CXX_COMPILER=g++-7 -DCMAKE_C_COMPILER=gcc-7]

1.b Python bindings for client

To build an experimental client-server model with python bindings, see the python folder.

2. Run C++ unit-tests

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

cd $HE_TRANSFORMER/build
# To run CKKS unit-test
./test/unit-test --gtest_filter="HE_SEAL_CKKS.*abc*"
# To run all C++ unit-tests
./test/unit-test

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
python axpy.py
# To run CKKS unit-test
NGRAPH_TF_BACKEND=HE_SEAL_CKKS python axpy.py

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

Code formatting

Please run maint/apply-code-format.sh before submitting a pull request.

About

nGraph-HE: Deep learning with Homomorphic Encryption (HE) through Intel nGraph

License:Apache License 2.0


Languages

Language:C++ 91.6%Language:CMake 4.3%Language:Shell 2.5%Language:Python 1.4%Language:Makefile 0.1%