Neural cryptography with feedback

TL;DR

This paper introduces a feedback mechanism in neural cryptography that enhances security by increasing repulsive forces, and demonstrates its effectiveness through simulations, analysis, and practical pseudorandom sequence generation.

Contribution

It presents a novel feedback approach in neural cryptography that improves security and enables pseudorandom sequence generation for encryption.

Findings

Feedback increases the probability of security against attacks.

Scaling laws show improved security with feedback.

Network with feedback can generate pseudorandom bit sequences.

Abstract

Neural cryptography is based on a competition between attractive and repulsive stochastic forces. A feedback mechanism is added to neural cryptography which increases the repulsive forces. Using numerical simulations and an analytic approach, the probability of a successful attack is calculated for different model parameters. Scaling laws are derived which show that feedback improves the security of the system. In addition, a network with feedback generates a pseudorandom bit sequence which can be used to encrypt and decrypt a secret message.