International Journal of Engineering Sciences & Emerging Technologies, April 2012. ISSN: 2231 – 6604 Volume 2, Issue 1, pp: 46-50 ©IJESET 46 A TRIPLE-KEY CHAOTIC NEURAL NETWORK FOR CRYPTOGRAPHY IN IMAGE PROCESSING Shweta B. Suryawanshi 1 , Devesh D. Nawgaje 2 1 Department of E&TC, SSGMCE, Shegaon, Amaravati University, suryawanshi.shweta@gmail.com 2 Department of E&TC, Sr. Faculty, SSGMCE, Shegaon, Amaravati University, dnawgaje@gmail.com ABSTRACT 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, a neural network can be used to generate secret key. Many methods using chaotic neural network for cryptography here in this paper ‘Triple key’ is using in the network to encrypt and decrypt the data. Three different parameters which are decided by user are used to scramble the image data and so hackers get many difficulties to hack the data hence providing more security. For simulation MATLAB software is used. The experimental results shows that algorithm successfully perform the cryptography and highly sensitive to the small changes in key parameters. K EYWORDS: Chaos, Cryptography, Decryption, Encryption, neural network. I. INTRODUCTION Artificial Neural Networks are massively parallel adaptive network which consist of non-linear computing elements called Neurons [3]. ANN has no. of applications in various fields like communication, control, instrumentation etc. The ANN is capable of performing on nonlinear input and output systems in the workspace due to its large parallel interconnections between different layers and its nonlinear processing characteristics. The working of artificial neural network is weighted sum of input signal and the connecting weight. The sum is added with bias or threshold and resultant signal is then considered or proposed for sigmoid nonlinear function. Cryptography is a word that has been derived from the Greek words for ‘Secret Writing’. Here sensitive information which is intelligible called plaintext is converted in to unintelligible form called cipher text and process is called Encryption. The reverse process is called Decryption. Many cryptographic algorithms use the secret value called key which is useful for encryption and decryption. [1,5]. Cryptography is exchanging the information between the related persons without leakage of information by unauthorized one. For this secure transmission or communication, data is encrypted at transmitter and decrypted at receiver. The encryption is obtained by scrambling the phase spectrum of original one, reverse process is used for decryption. [1,7]. the types of cryptography are Public, Secret and hash cryptography. If the same key is used at both for encryption and decryption then it is called as secret or symmetric cryptography and if different key is used then called public cryptography. Image has some features like bulk data capacity, high data redundancy so encryption of image is different than that of the text, so conventional methods of cryptography are giving poor response for image cryptography. Ordinary data can be kept secured using number of encryption methods like DES (Data encryption standard), TDES(triple), IDEA (international data encryption algorithm), but problems occurred for real time application like audio or video has to be encrypted. Due to large data size, computational complexity and real time constraints, encryption of multimedia data becomes difficult. so chaotic scrambling of an image is more desirable than conventional methods.[2]