Application of Machine Learning in Cryptography

Abstract

Generally, neural networks have been extremely bad at cryptographic operations as they have a tough time carrying out an easy XOR computation. While that holds true, it ends up that neural networks can protect their private information from other neural networks by discovering unique structure of encryption and decryption, without being taught a specific algorithm. This is a slightly upgraded design used for the paper "Learning to Protect Communications with Adversarial Neural Cryptography". The model used in this paper is coded in python programming language, trained and run on raspberry-pi which provide dedicated hardware for the design.