TF Encrypted

TF Encrypted is a framework for encrypted machine learning in TensorFlow. It looks and feels like TensorFlow, taking advantage of the ease-of-use of the Keras API while enabling training and prediction over encrypted data. Under the hood, TF Encrypted integrates state-of-the-art cryptography like secure multi-party computation, and homomorphic encryption. TF Encrypted aims to make privacy-preserving machine learning readily available, without requiring expertise in cryptography, distributed systems, or high performance computing.

TF Encrypted focuses on:

Usability: The API and its underlying design philosophy make it easy to get started, use, and integrate privacy-preserving technology into pre-existing machine learning processes.
Extensibility: The architecture supports and encourages experimentation and benchmarking of new cryptographic protocols and machine learning algorithms.
Performance: Optimizing for tensor-based applications and relying on TensorFlow's backend means runtime performance comparable to that of specialized stand-alone frameworks.
Community: With a primary goal of pushing the technology forward the project encourages collaboration and open source over proprietary and closed solutions.
Security: Cryptographic protocols are evaluated against strong notions of security and known limitations are highlighted.

See below for more background material, explore the examples, or visit the documentation to learn more about how to use the library. You are also more than welcome to join our Slack channel for all questions around use and development.

Installation

TF Encrypted is available as a package on PyPI supporting Python 3.5+ and TensorFlow 1.12.0+ which can be installed using:

pip3 install tf-encrypted

Alternatively, installing from source can be done using:

git clone https://github.com/tf-encrypted/tf-encrypted.git
cd tf-encrypted
pip3 install -r requirements.txt
pip3 install -e .

This latter is useful on platforms for which the pip package has not yet been compiled but is also needed for development. Note that this will get you a working basic installation, yet a few more steps are required to match the performance and security of the version shipped in the pip package, see the installation instructions.

Usage

The following is an example of simple matmul on encrypted data using TF Encrypted:

import tensorflow as tf
import tf_encrypted as tfe

def provide_input():
    # normal TensorFlow operations can be run locally
    # as part of defining a private input, in this
    # case on the machine of the input provider
    return tf.ones(shape=(5, 10))

# define inputs
w = tfe.define_private_variable(tf.ones(shape=(10,10)))
x = tfe.define_private_input('input-provider', provide_input)

# define computation
y = tfe.matmul(x, w)

with tfe.Session() as sess:
    # initialize variables
    sess.run(tfe.global_variables_initializer())
    # reveal result
    result = sess.run(y.reveal())

For more information, check out the documentation or the examples.

Roadmap

High-level APIs for combining privacy and machine learning. So far TF Encrypted is focused on its low-level interface but it's time to figure out what it means for interfaces such as Keras when privacy enters the picture.
Tighter integration with TensorFlow. This includes aligning with the upcoming TensorFlow 2.0 as well as figuring out how TF Encrypted can work closely together with related projects such as TF Privacy and TF Federated.
Support for third party libraries. While TF Encrypted has its own implementations of secure computation, there are other excellent libraries out there for both secure computation and homomorphic encryption. We want to bring these on board and provide a bridge from TensorFlow.

Background & Further Reading

The following texts provide further in-depth presentations of the project:

Growing TF Encrypted outlines the roadmap and motivates why TF Encrypted is a community project
Experimenting with TF Encrypted walks through a simple example of turning an existing TensorFlow prediction model private
Private Machine Learning in TensorFlow using Secure Computation further elaborates on the benefits of the approach, outlines the adaptation of a secure computation protocol, and reports on concrete performance numbers
Secure Computations as Dataflow Programs describes the initial motivation and implementation

Project Status

TF Encrypted is experimental software not currently intended for use in production environments. The focus is on building the underlying primitives and techniques, with some practical security issues postponed for a later stage. However, care is taken to ensure that none of these represent fundamental issues that cannot be fixed as needed.

Known limitations

Elements of TensorFlow's networking subsystem does not appear to be sufficiently hardened against malicious users. Proxies or other means of access filtering may be sufficient to mitigate this.

Support

Please open an issue or feel free to reach out directly on Slack.

Contributing

Check out our contribution guide for more information!

Don't hesitate to send a pull request, open an issue, or ask for help! You can do so either via GitHub or by joining our Slack channel.

The project was originally started by Morten Dahl but has since benefitted enormously from the efforts of several contributors, most notably Dropout Labs and members of the OpenMined community:

Morten Dahl (lead, Dropout Labs)
Ben DeCoste (Dropout Labs)
Yann Dupis (Dropout Labs)
Morgan Giraud (while at Dropout Labs)
Ian Livingstone (Dropout Labs)
Jason Mancuso (Dropout Labs)
Justin Patriquin (Dropout Labs)
Andrew Trask (OpenMined)
Koen van der Veen (OpenMined)
Gavin Uhma (Dropout Labs)

License

Licensed under Apache License, Version 2.0 (see LICENSE or http://www.apache.org/licenses/LICENSE-2.0). Copyright as specified in NOTICE.

gavinuhma/tf-encrypted