Adversarial-Neural-Cryptography

An implementation of the ICLR 2017 paper 'Learning to Protect Communications with Adversarial Neural Cryptography'.

Dependencies

Simply run:

pip install -r requirements.txt

Running the script

In order to start training the agents: Alice, Bob and Eve run:

python3 neural_encryption.py

To visualize the training graph during the run:

tensorboard --logdir logs