Artificial Neural Synchronization Using Nature Inspired Whale Optimization

Arindam Sarkar,Chinmay Chakraborty,Subhendu Kumar Pani,Moirangthem Marjit Singh,Mohammad Zubair Khan,Abdulfattah Noorwali

doi:10.1109/access.2021.3052884

Abstract

In this article, a whale optimization-based neural synchronization has been proposed for the development of the key exchange protocol. At the time of exchange of sensitive information, intruders can effortlessly perform sniffing, spoofing, phishing, or Man-In-The-Middle (MITM) attack to tamper the vital information. Information needs to be secretly transmitted with high level of encryption by preserving the authentication, confidentiality, and integrity factors. Such stated requirements urge the researchers to develop a neural network-based fast and robust security protocol. A special neural network structure called Double Layer Tree Parity Machine (DLTPM) is proposed for neural synchronization. Two DLTPMs accept the common input and different weight vectors and update the weights using neural learning rules by exchanging their output. In some steps, it results in complete synchronization, and the weights of the two DLTMs become identical. These identical weights serve as a secret key. There is, however, hardly any research in the field of neural weight vector optimization using a nature-inspired algorithm for faster neural synchronization. In this article, whale optimization-based DLTPM is proposed. For faster synchronization, this proposed DLTPM model uses a whale algorithm optimized weight vector. This proposed DLTPM model is faster and has better security. This proposed technique has been passed through a series of parametric tests. The results have been compared with some recent techniques. The results of the proposed technique have shown effective and has robust potential.

Highlights

Rosen-Zvi et al [11]; Lakshmanan et al [12] ; Ni and Paul [13] recently showed that neural cryptography has the capability of achieving key exchange through neural synchronization of Artificial Neural Networks (ANN)
The acceptance or rejection of the input vector is determined by a probability value (p-Value)
SCOPE For the cryptographic public-key exchange protocol, this article proposes the synchronization of Double Hidden Layer Neural Networks using nature-inspired whale optimization

Summary

Introduction

Diffie and Hellman key distribution algorithm [1] is the public-key exchange algorithm. It helps two communication systems to agree on the same encryption key by exchanging a key between them through an insecure medium. In a number of fields such as identification, authentication, data encryption and security, the secret keys are used. Innovative methods for the generation/exchange of cryptographic keys for a secure and low-cost protocol must be required. Rosen-Zvi et al [11]; Lakshmanan et al [12] ; Ni and Paul [13] recently showed that neural cryptography has the capability of achieving key exchange through neural synchronization of Artificial Neural Networks (ANN)

Methods

Results

Conclusion