比赛过程中使用的模型是预先训练好的，本仓库包含了训练所需代码以及 exp。writeup 之后再更新。
The model used during the competition was trained in advance. This repo contains all the codes needed for training, and also my exp. I am going to update my writeup here in a few days.
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.
- TensorFlow
- Numpy
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 96 --epochs 60
- carpedm20's DCGAN implementation in TensorFlow.
- Liam's implementation of Adversarial Neural Cryptography in Theano.
If you want to cite this code in your work, refer to the following DOI:
MIT