A Chaos-based Hybrid Image Encryption Scheme Using Dna Encoding and Deep Neural Network Key Generation
Year: 2025
Type: dissertation
Abstract: This repository contains the preprint of the research article entitled “A chaos-based hybrid image encryption scheme using DNA encoding and deep neural network key generation.” The study proposes a novel hybrid image encryption framework that integrates convolutional neural networks (CNNs) for plaintext-dependent dynamic key generation, a two-dimensional hyper-chaotic map for pixel permutation and diffusion, and dynamic DNA encoding for bit-level confusion. Unlike conventional chaos-based or DNA-based encryption schemes, the proposed method forms a fully coupled, adaptive architecture in which the plaintext image directly influences the cryptographic key stream and subsequent encryption stages. Extensive experimental evaluations on standard benchmark images demonstrate near-ideal cryptographic performance in terms of information entropy, differential attack resistance (NPCR and UACI), pixel correlation, key sensitivity, and robustness against noise and data loss. This version is a preprint and has been submitted to PLOS ONE for peer review. The content may be updated following the review process.
Author: alsaadi, lamis alsaadi
Institution: University of Babylon
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7115568871
Cites:
Cited by:
Related to: