Home

Awesome

EzPC: Easy Secure Multiparty Computation contributions welcome

Reference Papers:

SIGMA: Secure GPT Inference with Function Secret Sharing
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
PoPETS 2024

Orca: FSS-based Secure Training with GPUs
Neha Jawalkar, Kanav Gupta, Arkaprava Basu, Nishanth Chandran, Divya Gupta, Rahul Sharma
IEEE S&P 2024

Secure Floating-Point Training
Deevashwer Rathee, Anwesh Bhattacharya, Divya Gupta, Rahul Sharma, Dawn Song
USENIX Security 2023

SecFloat: Accurate Floating-Point meets Secure 2-Party Computation
Deevashwer Rathee, Anwesh Bhattacharya, Rahul Sharma, Divya Gupta, Nishanth Chandran, Aseem Rastogi
IEEE S&P 2022

SIRNN: A Math Library for Secure RNN Inference
Deevashwer Rathee, Mayank Rathee, Rahul Kranti Kiran Goli, Divya Gupta, Rahul Sharma, Nishanth Chandran, Aseem Rastogi
IEEE S&P 2021

CrypTFlow2: Practical 2-Party Secure Inference
Deevashwer Rathee, Mayank Rathee, Nishant Kumar, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma
ACM CCS 2020

CrypTFlow: Secure TensorFlow Inference
Nishant Kumar, Mayank Rathee, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma
IEEE S&P 2020

EzPC: Programmable, Efficient, and Scalable Secure Two-Party Computation for Machine Learning
Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma, Shardul Tripathi
IEEE EuroS&P 2019

Project webpage: https://aka.ms/ezpc

Introduction

This repository has the following components:

Each one of the above is independent and usable in their own right and more information can be found in the readme of each of the components. But together these combine to make CrypTFlow a powerful system for end-to-end secure inference of deep neural networks written in TensorFlow.

With these components in place, we are able to run for the first time secure inference on the ImageNet dataset with the pre-trained models of the following deep neural nets: ResNet-50, DenseNet-121 and SqueezeNet for ImageNet. For an end-to-end tutorial on running models with CrypTFlow please refer to this blog post.

Setup

For setup instructions, please refer to each of the components' readme.

Alternatively you can use the setup_env_and_build.sh script. It installs dependencies and builds each component. It also creates a virtual environment in a mpc_venv folder with all the required packages. If you want to do setup with default paths and settings do ./setup_env_and_build.sh quick, otherwise if you want to manually choose paths you can use ./setup_env_and_build.sh.

Please do source mpc_venv/bin/activate before using the toolchain.

Secure AI Validation

To setup the repo with modified SCI build such that only secret shares are revealed at the end of 2PC, run the setup script as ./setup_env_and_build.sh quick NO_REVEAL_OUTPUT. Alternatively, just rebuild SCI. For instructions to build modified SCI, see README for SCI.

To build docker image for Secure AI Validation, use the Dockerfile_AI_Validation dockerfile.

docker build -t ezpc_modified - < path/to/EzPC/Dockerfile_AI_Validation

Docker

You can use a pre-built docker image from docker hub using docker pull ezpc/ezpc:latest. We occasionally push stable images to that channel. However, if you want a docker image with the latest code, you can build it yourself using:

docker build -t ezpc_image - < path/to/EzPC/Dockerfile

Wiki

Wiki section of this repository provides coding practices and examples to get started with EzPC.

Issues/Bugs

For bugs and support, please create an issue on the issues page.