Note: This repository is no longer maintained.

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.

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

• carpedm20’s DCGAN implementation in TensorFlow.
• Liam’s implementation of Adversarial Neural Cryptography in Theano.

Citing Code

If you want to cite this code in your work, refer to the following DOI:

License

MIT