Enhancing Image Security via Block Cyclic Construction and DNA-Based LFSR

Abstract

The rapidly growing multimedia image data driven by real-time messaging technologies is particularly evident in applications such as autonomous vehicle tracking, smart cities, surveillance systems and many more. Considering images, data privacy and security are of paramount importance. Yet, many existing methods need to pay more attention to the specific challenges posed by chaotic maps, such as limited parameter coverage and insufficient chaotic behaviour. We present a novel method for image encryption that combines a cyclic block function during the confusion phase and a DNA-based Linear Feedback Shift Register (LFSR) in the diffusion phase to render the final cipher image. This process involves diagonal cyclic shifting and swapping of pixel blocks to minimize pixel correlation. DNA cryptography-based LFSR is particularly efficacious in high-quality pseudorandom number generation due to its robust statistical effects. Besides that, DNA-based operations improve the encryption speed, making the process more efficient. The proposed cryptosystem is validated through several methods, including histogram analysis, correlation assessment, entropy measurement, key sensitivity evaluation, and $\chi ^{2}$ testing. Our algorithm offers superior security and efficiency, outperforming established schemes in terms of security and robustness.