HOME JOURNALS CONTACT

Journal of Engineering and Applied Sciences

Classification and Identification of Classical Cipher Type using Artificial Neural Networks
Ahmed J. Abd and Sufyan T. Faraj Al-Janabi

Abstract: In this study, the capability of classifying the main types of classical ciphers systems is presented using Artificial Neural Networks (ANNs) starting from simplest form of information (natural text) and ending with more complex type of classical ciphers (periodic polyalphabetic system and polygraph system with 4 degree of key order). The aim of this study is to prove that all classical ciphers can be classified or identified depending on the degree of complexity of the ciphertext. This can be done by using 3 levels of classification. The obtained results showed that the proposed classifier can successfully classify the classical cipher systems. This is a clear success for the proposed classifier opening further research directions and can produce informative insights on the problem of identifying and classification of ciphertext produced by modern ciphers which is an important activity in automated cryptanalysis.

How to cite this article
Ahmed J. Abd and Sufyan T. Faraj Al-Janabi, 2019. Classification and Identification of Classical Cipher Type using Artificial Neural Networks. Journal of Engineering and Applied Sciences, 14: 3549-3556.

© Medwell Journals. All Rights Reserved