Information Encryption Based on the Synthesis of a Neural Network and AES Algorithm

This paper proposes a system of information encryption based on the synthesis of a neural network and AES(Advanced Encryption Standard(Rijndael)) algorithm. The encryption system is based on the diagonalized matrix of weight coefficients of synaptic connections of the neural network in the basis of...

Full description

Saved in:
Bibliographic Details
Published in2019 3rd International Conference on Advanced Information and Communications Technologies (AICT) pp. 447 - 450
Main Authors Lytvyn, Vasyl, Peleshchak, Ivan, Peleshchak, Roman, Vysotska, Victoria
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2019
Subjects
Advanced Encryption Standard
Biological neural networks
cryptosystem
diagonalization the weight matrices of synaptic connections
Encryption
Information systems
neural network
Neurons
Online AccessGet full text
DOI10.1109/AIACT.2019.8847896

Cover

More Information
Summary:This paper proposes a system of information encryption based on the synthesis of a neural network and AES(Advanced Encryption Standard(Rijndael)) algorithm. The encryption system is based on the diagonalized matrix of weight coefficients of synaptic connections of the neural network in the basis of vectors of input images, which provides the formation of a new key for each input image. The proposed approach provides a constantly changing key when encrypting information, that is, increases the degree of cryptographic stability of the algorithm compared to existing encryption algorithms.
DOI:10.1109/AIACT.2019.8847896