Image encryption approach using improved chaotic system incorporated with differential evolution and genetic algorithm

Meta-heuristic techniques are widely used to solve different complex real-life problems in recent scenarios. In this work, traditional key-generation mechanisms have been combined with meta-heuristic techniques to derive new key generation models in chaos-based image cryptography. Initially, one among the key-strings has been generated using the logistic map approach that is known for its ability to produce effective chaotic performance. In this paper, the chaotic effect of the key-string generated by the logistic map has further been enhanced by the application of differential evolution (DE), a population-based meta-heuristic optimization algorithm. This improved key sequence is used to produce chaotic a map which has been applied to images for diffusion operation. The confusion operation on the other hand is performed by the transposition process using another key-string produced by the application of another meta-heuristic technique, namely, Genetic Algorithm (GA). After thorough experimental works, the results have been compared with the state-of-the-art and it is observed that the approach proposed here provides strong cryptographic behavior in terms of information entropy, key sensitivity, robustness against noise, and hereby stands against all kinds of statistical and differential attacks including brute force.