# Introduction ryptography 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 [1]. Cryptosystems are commonly used for protecting the integrity, confidentiality, and authenticity of information resources. In addition to meeting standard specifications relating to encryption and decryption, such systems must meet increasingly stringent specifications concerning information security. This is mostly due to the steady demand to protect data and resources from disclosure, to guarantee the authenticity of data, and to protect systems from web based attacks. For these reasons, the development and evaluation of cryptographic algorithms is a challenging task [2]. This paper is study and performance of ANN Based Chaotic Generator in the filed of Cryptography. The rest of the paper is organized as follows: section 2 discusses background and related work in the field of chaotic neural network based cryptography, section 3 Author ? ? ? : VITS Jabalpur, University of R.G.P.V. Bhopal M.P. e-mails: sona.mishra2909@gmail.com, amit_2440@yahoo.co.in discusses implementation section 4 discusses experimental report and test result and finally section 5 discusses conclusion. # II. # Background and Related Work Ilker DALKIRAN, Kenan DANIS¸MAN introduced a research paper on Artificial neural network based chaotic generator for cryptology. In this paper, to overcome disadvantages of chaotic systems, the dynamics of Chua's circuit namely x, y and z were modeled using Arti ficial Neural Network (ANN). ANNs have some distinctive capabilities like learning from experiences, generalizing from a few data and nonlinear relationship between inputs and outputs. The proposed ANN was trained in diffrent structures using different learning algorithms. To train the ANN, 24 different sets including the initial conditions of Chua's circuit were used and each set consisted of about 1800 input-output data. The experimental results showed that a feedforward Multi Layer Perceptron (MLP), trained with Bayesian Regulation back propagation algorithm, was found as the suitable network structure. As a case study, a message was first encrypted and then decrypted by the chaotic dynamics obtained from the proposed ANN and a comparison was made between the proposed ANN and the numerical solution of Chua's circuit about encrypted and decrypted messages [ # b) Proposed Work In Cryptography, secret key generation scheme was proposed by ANN based Chaotic Generator. ANN based chaotic Generator system used chaotic neural network scheme for encryption and decryption [7]. In this paper ANN based chaotic generator is proposed for data encryption and decryption, it produces the outputs according to initial conditions and control parameter .We improve the level of performance of chaos based cryptography [10] using binary value of ASCII Code of A to Z letter instead of decimal value. A plain-text was encrypted and then obtained cipher text was decrypted by using the chaotic dynamics (control parameter and initial point), initial condition and control parameter act as a secret key in the field of cryptography. It is accepted that the initial conditions which were used in the training phase of the ANN model and the system parameters are known by both the transmitter and the receiver. We adopted ANN based chaotic generator approach from et.al. [3] and increase the level of security from et. al. [10] and demonstrate by experimental result. # III. # Implementation A network is called chaotic neural network if its weights and biases are determined by chaotic sequence. In this section we use a algorithm for performing encryption and decryption using chaotic neural network. ANN based chaotic generator Using CNN scheme for encryption and decryption. Step 1. The chaotic Logistic map. # Set the value of M. Step 2. The secret key is the control parameter ? and the initial point x (0) of the Logistic map, which are all Lbit binary decimals. Determine parameter ? and initial point x (0). Step 3. The initialization procedure: Generate the chaotic sequence x(1), x(2), x(3)? . . Step 4. The encryption procedure: Depending upon the chaotic sequence a weight matrix and a bias matrix is obtained and the net input is obtained. Then a hard limiter is applied as a transfer function in order to obtain the digital encrypted data. For decryption the same network is used and the same initial value is used to generate the chaotic sequence and for decrypting the data successfully. Step 5. The decryption procedure The decryption procedure is the same as the above one except that the input signal to the decryption Chaotic neural network should be g'(n) and its output signal should be g"(n). V. # b) ANN based chaotic Generator # Conclusion It is clear that the binary value sequence of ASCII CODE is encrypted and decrypted correctly by knowing the exact values of x (0) and µ otherwise we get the wrong value sequences .And also clear that the binanry value is more strong enough as compre to decimal values. In this paper we successfully perform encryption and decryption with the help of Chaotic neural network and improve the level of security with the help of using binanry value of ASCII Code instead of decimal values . Network was trained with the help of back propagation algorithm in neural network. Above experiment clear that the Binary value of ASCII CODE is encrypted and its decrypted with same value of parameter , encrypted value is decrypt only correctly by knowing the exact values of x (0) and µ otherwise we get the wrong generated value sequences . ANN based Chaotic generator provide high range of security in the field of cryptography. ![a) Problem DefinitionIn now a day's secret key generation in the field of cryptography continues to be an active research field, as shown by the large number of papers being published. In this previous published research work now we are study their performance and various different way to perform cryptography [9]. We considered chaos based cryptography [3] [10]. but I found that the adopted approaches of perform cryptography and generating secret key is very complex , time consuming and providing limited security during encryption in transmission end or decryption in receiving end. A Problem is arises Unauthorized user or hackers easily guess or predict secret key and view our confidential data and damage or modify it.](image-2.png "") ![x(M) by the formula x(n + 1) = ?x(n) (1 -x(n)) and create b(0), b(l), ..., b(8M -1) from x(l), x(2),..., x(M) by the generating scheme that 0.b(8m -8)b(8m -7)?.. b (8m -2) b(8m -l) ? is the binary representation of x(m) for m = 1, 2,. . . .,M.](image-3.png "") 2![Journal of C omp uter S cience and T echnology Volume XV Issue I Version I Year ( ) D 2015 Enhance the Performance of Chaotic Generator in the Filed of Cryptography: A Secret Key Generation Approach ?x(i ? 1)(1 ? x(i ? 1)) Key Cryptography Through chaotic neural network g = digital signal of length M and g (n) 0 ? M-1 , be the one-byte value of the signal g at position n.](image-4.png "2 GlobalFor") :![Figure : ANN based chaotic Generator Working of Encryption and Decryption Using ANN Based Chaotic Generator 1. In the transmitter, software based control unit decides the values of initial conditions and the ANN based chaotic generator produces the outputs according to those initial conditions. 2. In our experiment ASCII Char A to Z Binary value was chosen as a plain-text. 3. The cipher-text is obtained by adding normalized data to the chaotic dynamic (? and x).](image-5.png "Figure :") ![4. A tail which consists of initial condition, andnormalization parameters, is tied to the cipher-text by the control unit and then the cipher-text with tail is transmitted. 5. In the decryption phase, the tail is firstly discriminated from the cipher-text and the initial conditions are extracted from the tail by the control unit. 6. Then, the initial conditions are applied to the ANN based chaotic generator and the chaotic dynamic (? and x) is produced by the generator, initial condition x and control parameter is act as secret key. 7. Finally the plain-text is obtained by subtracting the chaotic dynamic (? and x) from the cipher-text. The size of cipher-text is equal to the size of plain-text. But tying the tail to the cipher-text enlarges the size of encrypted data. The size of tail is only 8 bytes IV.Experiment and Test Result a) Secret Key Cryptography by chaotic neural networkA chaotic network is a neural network whose weights depend on a chaotic sequence. The chaotic sequence highly depends upon the initial conditions and the parameters, x (0) and µ are set. It is very difficult to decrypt an encrypted data correctly by making an exhaustive search without knowing x (0) and µ ().b) ANN based chaotic GeneratorExample-Binary value of ASCII CODE 'A' Encryted with deiffrent Initial Conditions (Values of x (0) and µ ()).Global Journal of C omp uter S cience and T echnologyVolume XV Issue I Version I of Chaotic Generator in the Filed of Cryptography: A Secret Key Generation Approach Decryption with same Initial conditions as below --It is clear from Example 01. that the binary value sequence of ASCII CODE A is encrypted and decrypted correctly by knowing the exact values of x (0) and µ otherwise we get the wrong value sequences and also cleared that the Binary values of ASCII Code is more strong as compared to decimal values of ASCII Code , no longer pridiction is possible of binanry values. Initial point x (0) and control parameter µ is act as a secret key.](image-6.png "") NETWORKS IN CRYPTOSYSTEMS. This paper presentsa review of the literature on the use of artificial neutralnetworks in cryptography. Different neural networkbased approaches have been categorized based ontheir applications to different components ofcryptosystems such as secret key protocols, visualcryptography, design of random generators, digitalwatermarking, and steganalysis[2].KARAM M. Z. OTHMAN , MOHAMMED H. ALJAMMAS introduced IMPLEMENTATION OF NEURAL -CRYPTOGRAPHIC SYSTEM USING FPGA. In this work,a Pseudo Random Number Generator (PRNG) based onartificial Neural Networks (ANN) has been designed.This PRNG has been used to design stream ciphersystem with high statistical randomness properties of itskey sequence using ANN. Software simulation has beenbuild using MATLAB to firstly, ensure passing four well-known statistical tests that guaranteed randomnesscharacteristics [6].An Empirical Investigation of Using ANN BasedN-Keywords: ann based chaotic generator, chaotic neuralnetwork, cryptography.3].Jason L. Wright , Milos Manic Proposed aresearch paper onNeural Network Approach toLocating Cryptography in Object Code. In this paper,artificial neural networks are used to classify functionalblocks from a disassembled program as being eithercryptography related or not. The resulting system,referred to as NNLC (Neural Net for LocatingCryptography) is presented and results of applying thissystem to various libraries are described.[4].EvaVolna,MartinKotyrba,VaclavKocian,Michal Janosek developed a CRYPTOGRAPHYBASED ON NEURAL NETWORK. This paper deals withusing neural network in cryptography, e.g. designingsuch neural network that would be practically used inthe area of cryptography. This paper also includes anexperimental demonstration [5].T. SCHMIDT, H. RAHNAMA developed A REVIEW OF APPLICATIONS OF ARTIFICIAL NEURAL Abstract © 2015 Global Journals Inc. (US) 1 © 2015 Global Journals Inc. (US) * Nawgaje-a triple-key chaotic neural network for cryptography in image processing BShweta Suryawanshi DDevesh International Journal of Engineering Sciences & Emerging Technologies 2231 -6604 2 1 April 2012 * of computer science, ryerson university, canada -a review of applications of artificial neural networks in cryptosystems TSchmidt Dept