The International Journal of Engineering and Science (IJES) || Volume || 8 || Issue || 12 || Series I || Pages || PP 67-70|| 2019 || ISSN (e): 2319 – 1813 ISSN (p): 23-19 – 1805 DOI:10.9790/1813-0812016770 www.theijes.com Page 67 Image encryption using chaotic neural network Sushil Kumar Computer Science and engineering, Maharaja Surajmal institute of technology, New Delhi, India --------------------------------------------------------------ABSTRACT------------------------------------------------------ The present work proposes the implementation of Wavelet based Chaotic Neural Network (WCNN) for image encryption. The neural network used is chaotic in nature i.e. its weights and bias will be determined by chaotic sequence with the help of 1-D logistic map. Private key system is achieved with the help of initial conditions. WCNN provides two level security along with the data compression to be transmitted. The image is first encrypted and then decrypted using WCNN. Encryption is carried out using only approximate coefficients, which reduces the transmitted data to a large extent. CNN is also applied for comparison purpose. The proposed methodology is applied on standard and real images. Further the behavior of system is verified with different key values at the receiver end and the proposed encryption scheme is proved to be keysensitive. KEYWORDS: -CNN, WCNN, Chaotic Cryptography. --------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: 10-12-2019 Date of Acceptance: 29-12-2019 --------------------------------------------------------------------------------------------------------------------------------------- I. INTRODUCTION A computer network has created a revolution in the field of communication. Internet enables millions of people to communicate. Confidential communication is common practice in the social life. However, as information communicated on shared network, it is exposed in public domain and may lead to undesirable results. The communicated information must be secured from public access, illegal changes and accessible to authorized users. The digital images can be secured by using [1] cryptography, steganography and watermarking. An approach to achieve confidential or secure communication is called cryptography. It is a technique for converting intelligible message to unintelligible forms. Steganography is a technique of hiding secret information whereas watermarking hides the proprietary information. The image data has redundancy, large size and high correlation between pixels. Therefore conventional encryption methods can‟t be easily applied to images. The image encryption requires real -time processing, format consistency, and image compression. The real-time image processing is a challenging task as these requirements must be accomplished along with secured communication. II. LITERATURESURVEY Mitra A et al. [1] used bit, pixel and block permutations for combinational image encryption. The permutation of bits significantly reduces the correlation and therefore perceptual information is decreased, whereas the permutation of pixels and blocks achieve better security in comparison to bit permutation.Kede Ma et.al [2] used reversible data hiding for image encryption by reserving room. The proposed technique extracts the data and image is recovered without error i.e. real reversibility is achieved. The reversible data hiding with distributed source encoding is suggested by Zhenxing Qian et. al[3]. The proposed method proves to be better than the techniques available in literature. Ran Tao et.al [4] suggested multi-order fraction Fourier Transform based image encryption. The results show that image decryption is sensitive to transform order. Jiantao Zhou et. al[5] designed a prediction error clustering and random permutation based image encryption-then-compression system. The proposed approach is comparable to other techniques in terms of compression efficiency. Xinpeng Zhang et. al [6] proposed a scalable coding for encrypted images and the original image is successfullyreconstructed. III. SYSTEM MODEL A. ChaoticCryptography Confusion and diffusion are two properties of the operation of a secure cipher which are discussed by Claude Shannon. Chaotic systems are deterministic and highly dependent on initial conditions and parameters. This implies that behavior of chaotic systems is modeled by mathematical equations. G. Jakimoski and L. Kocarev [7] suggested and analyzed chaos based cryptography using exponential and logistic chaotic maps. The technique is successfully applied on Feistel network.