A survey on machine learning applied to symmetric cryptanalysis

In this work we give a short review of the recent progresses of machine learning techniques applied to cryptanalysis of symmetric ciphers, with particular focus on artificial neural networks. We start with some terminology and basics of neural networks, to then classify the recent works in two categories: "black-box cryptanalysis", techniques that not require previous information about the cipher, and "neuro-aided cryptanalysis", techniques used to improve existing methods in cryptanalysis.