Encryption function on artificial neural network. Issue 8 (November 2016)

• Record Type: Journal Article
• Authors: Al Azawee, Haitham; Husien, Sabah; Yunus, Mohd
• Is Part Of: Neural computing & applications. Volume 27:Issue 8(2016)
• Page Start: 2601
• Page End: 2604
• Publication Date: 2016-11
• Subjects: Artificial neural network -- Image encryption -- Human–computer interaction -- Image decryption -- Computer vision; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-2028-3
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract Six algorithms that design secrecy keys are used for digital image encryption. The privacy keys generated by stream cipher generators were tested for their randomness applying five tests of randomness. The images generated by applying each algorithm were tested for their regularity and residual intelligibility. The histograms for images ciphered by stream cipher schemes all have approximately flat histogram less information as compared to one-dimensional ciphering algorithms and threshold generator-based image ciphering scheme. Furthermore, the stream cipher schemes were effectively applied to the colored images of 256-color levels of true-color images (24 bit). In this paper, we try to decrypt automatically using artificial neural network by decryption through multilayer perceptron and radial basis function; networks were tested using the interface by calculating the error rates of decrypted images.