Cryptography based on Artificial Neural Network

ABSTRACT A Neural Network is a machine that is designed to model the way in which the brain performs a task or function of interest. It has the ability to perform complex computations with ease. The objective of this project was to investigate the use of ANNs in various kinds of digital circuits as well as in the field of Cryptography. During our project, we have studied different neural network architectures and training algorithms. Cryptography is a technique to make information unreadable for unauthorized users. Today, building a secure channel is one of the most challenging areas for research in communication systems. Many forms of public key cryptography are available, but it requires more complex techniques and needs more computational power. This paper aims at implementation of cryptography using neural networks that will alleviate these problems. Neural network and cryptography together can make a great help in field of networks security. The key formed by neural network is in the form of weights and neuronal functions which is difficult to break. Here, text data would be use as an input data for cryptography so that data become unreadable for attackers and remains secure from them. Two neural networks are required to be used here, one for encryption process and another for decryption process.