Cryptography Using Neural Network

Abstract

The goal of any cryptographic system is the exchange of information among the intended users without any leakage of information to others who may have unauthorized access to it. In 1976, Diffie & Hellmann found that a common secret key could be created over a public channel accessible to any opponent. Since then many public key cryptography have been presented which are based on number theory and they demand large computational power. Moreover the process involved in generating public key is very complex and time consuming. To overcome these disadvantages, the neural networks can be used to generate common secret key. This is the motivation for this present work on interacting neural networks and cryptography[1].In the case of neural cryptography, both the communicating networks receive an identical input vector, generate an output bit and are trained based on the output bit. The dynamics of the two networks and their weight vectors is found to exhibit a novel phenomenon, where the networks synchronize to a state with identical time-dependent weights. This concept of synchronization by mutual learning can be applied to a secret key exchange protocol over a public channel. The generation of secret key over a public channel has been studied and the generated key is used for encrypting and decrypting the given message using DES algorithm which is simulated and synthesized using VHDL