Synchronization of Tree Parity Machines using non-binary input vectors

TL;DR

This paper proposes a method to improve neural cryptography by using non-binary input vectors in tree parity machines, leading to faster synchronization and enhanced security.

Contribution

It introduces a novel approach of employing wider-range input vectors for neural network synchronization, reducing synchronization time and increasing security.

Findings

Synchronization duration is reduced.

Number of bit exchanges needed is decreased.

Security of neural cryptography is improved.

Abstract

Neural cryptography is the application of artificial neural networks in the subject of cryptography. The functionality of this solution is based on a tree parity machine. It uses artificial neural networks to perform secure key exchange between network entities. This article proposes improvements to the synchronization of two tree parity machines. The improvement is based on learning artificial neural network using input vectors which have a wider range of values than binary ones. As a result, the duration of the synchronization process is reduced. Therefore, tree parity machines achieve common weights in a shorter time due to the reduction of necessary bit exchanges. This approach improves the security of neural cryptography