Application of artificial neural networks in the classification of classical encryption algorithms
Abstract
Cryptography, which has a long historical process, has different encryption algorithms. The first step of any cryptanalysis is to try to determine what type of encryption method that ciphertext uses. This cannot be easy in any process because many types of encryption are currently available. This problem can be solved using artificial neural networks. In this study, we developed a model that discriminates the type of Affine, Playfair, and Vigenere encryption algorithms using neural networks. The research software is based on the Python programming language and its TensorFlow library, as well as Keras. This paper presents the current advances in research on the use of artificial neural networks for cypher-type detection. A built-in neural network can correctly classify encrypted texts by about 95%. The article reveals the possibilities of determining the type of encryption based on an artificial neural network. It can be seen that new methods of cryptanalysis can be developed from artificial neural networks.