Neural Networks-Based Cryptography: A Survey

A current trend of research focuses on artificial intelligence based cryptography which although proposed almost thirty years ago could not attract much attention. Abadi and Anderson’s work adversarial in 2016 rejuvenated the area now building neural networks that are able to learn using idea from Generative Adversarial Networks (GANs). In this paper, we survey most prominent works cover two main periods. The first period covers oldest models have been shortly after 2000 second more recent since 2016. We discuss implementation systems earlier era attacks mounted them. After that, focus post where advanced techniques utilized rely GANs compete with each other order achieve a goal e.g. learning encrypt communication. Finally, security analysis performed models.