Semi-chaotic mutual learning platform for key-exchange algorithm using neural network

Abstract EN

Neural ne twork has been emerged the cry ptography field as efficient tool for both cry ptanaly sis and cry ptography due to its amazing ability to explore solution spac e for a given problem.

One of the latest observations for the behavior of neural networks is its ability to sy nchronize itself to other neural network based on mutual learning rules; this phenomenon has been under the focus of specialist in cry ptographic field due to its significant usage as highly secure key exc hange algorithm.

This paper is presenting new approach to drive the sy nchronization base d on semi-chaotic mutual le arning, where the output of eac h neural network will be extracted through non-linear mapping to memory filled with balanc ed number of 1's and 0's as this pape r will demonstrate.