Hybridization of Genetic Algorithm with Neural Networks to Cipher English Texts

• Main Authors: Radwan Al-Jawadi, Raid Al-Naima
• Format: Article
• Language: Arabic
• Published: Mosul University 2010-12-01
• Series: Al-Rafidain Journal of Computer Sciences and Mathematics
• Subjects: genetic algorithm; neural networks; stream cipher; english texts
• Online Access: https://csmj.mosuljournals.com/article_163928_b64f4f594bcc7891fbbd9de34d9d51e7.pdf

This research aims in the first stage to built a cipher system using hybrid Genetic Algorithm with single layer Neural network to prevent any data attack during the transition process , where the ASCII of the letters are used as inputs to the network and the random numbers are used as outputs to the network , then the weights will be constructed after the network training . In the second stage a decipher process is used to restore the ciphered data by using the inverse of the genetic neural network , where the inverse of weights is used as a key for the decryption process . Stream cipher method is used to input the data in the network during the ciphering stage. This suggested technique attained 100% success. All the ciphering and deciphering processes are built under MATLAB ver.(7) .