Loading…

Advanced hybrid color image encryption utilizing novel chaotic neural network and 5D-hyperchaotic system

This paper introduces a new image encryption technique, leveraging the combined effects of a chaotic neural network and a 5D-Hyperchaotic system (HCS). The proposed method involves chaotic image matrix generation through the integration of the Ikeda map within an artificial neural network, followed...

Full description

Saved in:
Bibliographic Details
Published in:Evolutionary intelligence 2024, Vol.17 (4), p.3043-3059
Main Authors: Pal, Subhashish, Mukhopadhyay, Jaya, Pathak, Arghya, Mondal, Hrishikesh, Mandal, Mrinal Kanti
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces a new image encryption technique, leveraging the combined effects of a chaotic neural network and a 5D-Hyperchaotic system (HCS). The proposed method involves chaotic image matrix generation through the integration of the Ikeda map within an artificial neural network, followed by diffusion and confusion to enhance security. The 5D-HCS generates chaotic sequences using image data and a cryptographic key, which are then incorporated to produce a highly secure encrypted image. The proposed algorithm is rigorously validated through comprehensive testing like NIST suite evaluations, correlation analysis, key sensitivity assessment, and venerability to various attacks, yielding notable results such as an entropy value of 7.9992, an NPCR of 99.6, and an UACI of 33.463 for the encrypted Lena image. This study promises the method’s efficacy in safeguarding sensitive visual data and positions it as an avenue for future research in image encryption as an emerging technology.
ISSN:1864-5909
1864-5917
DOI:10.1007/s12065-024-00927-6