Cryptography Using Chaotic Neural Network

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 and Hellmann found that a common secret key could be created over 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 this disadvantage, the neural network can be used to generate common secret key. In this particular paper chaotic neural network is proposed for data encryption. Chaos is defined as stochastic behavior occurring in deterministic system [6]. It is known that chaotic systems are non – periodical and also sensitive to initial conditions, system parameters and topological transitivity [4]. The main reason of using chaotic system in cryptography is especially noise like non – periodic dynamics of these systems.