Neural Networks that invent their own encryption 🔑
Python
Latest commit 40ca6e8 Nov 21, 2016 @ankeshanand Minor fixes
Permalink
Failed to load latest commit information.
assets Add setup diagram Nov 15, 2016
src Minor fixes Nov 21, 2016
.gitignore Initial Commit Nov 15, 2016
LICENSE.txt Create LICENSE.txt Nov 15, 2016
README.md Update README.md Nov 15, 2016
main.py Minor fixes Nov 21, 2016
requirements.txt Initial Commit Nov 15, 2016

README.md

Adversarial Neural Cryptography in TensorFlow

A Tensorflow Flow implementation of Google Brain's recent paper (Learning to Protect Communications with Adversarial Neural Cryptography.)

Two Neural Networks, Alice and Bob learn to communicate secretly with each other, in presence of an adversary Eve.

Setup

Pre-requisites

  • TensorFlow
  • Seaborn (for plots)
  • Numpy

Usage

First, ensure you have the dependencies installed.

$ pip install -r requirements.txt

To train the neural networks, run the main.py script.

$ python main.py --msg-len 32 --epochs 50

Attribution / Thanks

License

MIT