ENCRYPTION AND DECRYPTION USING ARTIFICIAL NEURAL NETWORK

Abstract: The project elaborating Artificial Neural Network, its various characteristics and business applications. A Neural Network is a machine which is designed to work like brain. It has the ability to perform complex calculations with ease. Cryptography is the exchange of information among the users without leakage of information to others. Many public key cryptography are available which are based on number theory but it has the drawback of requirement of large computational power, complexity and time consumption during generation of key. To overcome these drawbacks, we analyzed neural network is the best way to generate secret key. In this paper we proposed a very new approach in the field of cryptography. We are using two artificial, neural networks in the field of cryptography. First One is ANN based n-state sequential machine and Other One is chaotic neural network. In our project, we have learned different neural network architectures as well as training algorithms. Sequential machine is successfully implemented using a Jordan network, trained with back-propagation algorithm. This sequential machine was used for encryption with the starting key as the key for decryption process. Chaotic neural network is also used for Cryptography.

Keywords: Artificial neural network, cryptography, sequential machine, chaotic neural network, Jordan network