# Information-Theoretic Medical Image Encryption via LLE-Verified Chaotic Keystreams and DNA Diffusion

## TL;DR

This paper introduces a new medical image encryption method using chaotic keystreams and DNA diffusion to achieve high security and remove spatial redundancy.

## Contribution

The novelty lies in combining chaos verification via LLE with LSTM-generated keystreams and DNA-based diffusion for medical image encryption.

## Key findings

- The encryption achieved near-maximum Shannon entropy (7.99–8.00 bits per channel) and strong differential security metrics.
- Key space analysis showed robustness with an order of magnitude of 2^384.
- Chaos verification improved keystream statistical quality and encryption decorrelation.

## Abstract

We propose an information-theoretic encryption scheme consisting of a four-dimensional chaotic map driver in combination with a prediction model using an LSTM neural net to generate a keystream, which was limited only after passing a test based on the largest Lyapunov exponent (LLE). Our security analysis used a permutation phase to remove spatial redundancy, which was followed by an invertible DNA cross-diffusion procedure based on RGB channels. The removal of uncertainty and redundancy was measured using Shannon’s entropy (7.99–8.00 bits per channel), pixel intercorrelation, and differential analysis (NPCR ≈ 99.6%, UACI ≈ 33.3%). In key space analysis (order ≈ 2384), self-right veneering with complete encryption validity was demonstrated in perfect decryptability. We explain how chaos verification enhances the statistical goodness of keystreams and provide ablations that separate each element’s influence on entropy and decorrelation.