Doing Cryptography in Tensorflow

After building a system with TensorFlow in Autumn 2017 and taking a course on Cryptography in Winter 2018, I saw some interesting parallels. TensorFlow is Machine Learning framework but under the hood it’s a general platform for doing computations in the structure of a graph. Cryptographic algorithms are frequently structured as the manipulation of vectors or matrices in the structure of a graph. I put together a Python notebook to explore this interesting relationship. Check it out on Kaggle.

Screenshot of the aforementioned Kaggle kernel.