A robust image-based cryptology scheme based on cellular non-linear network and local image descriptors

TL;DR

This paper introduces a novel cryptology scheme combining cellular nonlinear networks and local image descriptors, enhancing security and robustness in image encryption and steganography through chaotic maps and dynamic embedding.

Contribution

It presents a new cryptology framework using 3D CNN-generated chaotic maps and feature-based keys, improving security and adaptability over traditional fixed-key methods.

Findings

Effective encryption and steganography demonstrated on 25 standard images.

Enhanced security and robustness confirmed through visual and complexity analyses.

Dynamic $k$-LSB steganography improves data hiding capacity.

Abstract

Cellular nonlinear network (CNN) provides an infrastructure for Cellular Automata to have not only an initial state but an input which has a local memory in each cell with much more complexity. This property has many applications which we have investigated it in proposing a robust cryptology scheme. This scheme consists of a cryptography and steganography sub-module in which a 3D CNN is designed to produce a chaotic map as the kernel of the system to preserve confidentiality and data integrity in cryptology. Our contributions are three-fold including (1) a feature descriptor is applied to the cover image to form the secret key while conventional methods use a predefined key, (2) a 3D CNN is used to make a chaotic map for making cipher from the visual message, and (3) the proposed CNN is also used to make a dynamic $k$-LSB steganography. Conducted experiments on 25 standard images prove the effectiveness of the proposed cryptology scheme in terms of security, visual, and complexity analysis.