Hybrid encryption technique: Integrating the neural network with distortion techniques

This paper proposes a hybrid technique for data security. The computational model of the technique is grounded on both the nonlinearity of neural network manipulations and the effective distortion operations. To accomplish this, a two-layer feedforward neural network is trained for each plaintext bl...

Full description

Saved in:
Bibliographic Details
Main Author: Abu Zitar, Raed (author)
Other Authors: Al-Muhammed, Muhammed J. (author)
Published: 2022
Online Access:https://depot.sorbonne.ae/handle/20.500.12458/1307
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1857415063174905856
author Abu Zitar, Raed
author2 Al-Muhammed, Muhammed J.
author2_role author
author_facet Abu Zitar, Raed
Al-Muhammed, Muhammed J.
author_role author
dc.contributor.none.fl_str_mv Chakchai So-In
dc.creator.none.fl_str_mv Abu Zitar, Raed
Al-Muhammed, Muhammed J.
dc.date.none.fl_str_mv 2022-09-30T07:14:57Z
2022-09-30T07:14:57Z
2022
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0274947
https://depot.sorbonne.ae/handle/20.500.12458/1307
10.1371/journal.pone.0274947
dc.language.none.fl_str_mv en
dc.relation.none.fl_str_mv PLOS ONE
1932-6203
dc.title.none.fl_str_mv Hybrid encryption technique: Integrating the neural network with distortion techniques
dc.type.none.fl_str_mv Controlled Vocabulary for Resource Type Genres::text::periodical::journal::contribution to journal::journal article
description This paper proposes a hybrid technique for data security. The computational model of the technique is grounded on both the nonlinearity of neural network manipulations and the effective distortion operations. To accomplish this, a two-layer feedforward neural network is trained for each plaintext block. The first layer encodes the symbols of the input block, making the resulting ciphertext highly uncorrelated with the input block. The second layer reverses the impact of the first layer by generating weights that are used to restore the original plaintext block from the ciphered one. The distortion stage imposes further confusion on the ciphertext by applying a set of distortion and substitution operations whose functionality is fully controlled by random numbers generated by a key-based random number generator. This hybridization between these two stages (neural network stage and distortion stage) yields a very elusive technique that produces ciphertext with the maximum confusion. Furthermore, the proposed technique goes a step further by embedding a recurrent neural network that works in parallel with the first layer of the neural network to generate a digital signature for each input block. This signature is used to maintain the integrity of the block. The proposed method, therefore, not only ensures the confidentiality of the information but also equally maintains its integrity. The effectiveness of the proposed technique is proven through a set of rigorous randomness testing.
id sorbonner_d5653898c8fe900591cf06081eb2a813
identifier_str_mv 10.1371/journal.pone.0274947
language_invalid_str_mv en
network_acronym_str sorbonner
network_name_str Sorbonne University Abu Dhabi repository
oai_identifier_str oai:depot.sorbonne.ae:20.500.12458/1307
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Hybrid encryption technique: Integrating the neural network with distortion techniquesAbu Zitar, RaedAl-Muhammed, Muhammed J.This paper proposes a hybrid technique for data security. The computational model of the technique is grounded on both the nonlinearity of neural network manipulations and the effective distortion operations. To accomplish this, a two-layer feedforward neural network is trained for each plaintext block. The first layer encodes the symbols of the input block, making the resulting ciphertext highly uncorrelated with the input block. The second layer reverses the impact of the first layer by generating weights that are used to restore the original plaintext block from the ciphered one. The distortion stage imposes further confusion on the ciphertext by applying a set of distortion and substitution operations whose functionality is fully controlled by random numbers generated by a key-based random number generator. This hybridization between these two stages (neural network stage and distortion stage) yields a very elusive technique that produces ciphertext with the maximum confusion. Furthermore, the proposed technique goes a step further by embedding a recurrent neural network that works in parallel with the first layer of the neural network to generate a digital signature for each input block. This signature is used to maintain the integrity of the block. The proposed method, therefore, not only ensures the confidentiality of the information but also equally maintains its integrity. The effectiveness of the proposed technique is proven through a set of rigorous randomness testing.Chakchai So-In2022-09-30T07:14:57Z2022-09-30T07:14:57Z2022Controlled Vocabulary for Resource Type Genres::text::periodical::journal::contribution to journal::journal articleapplication/pdf10.1371/journal.pone.0274947https://depot.sorbonne.ae/handle/20.500.12458/130710.1371/journal.pone.0274947enPLOS ONE1932-6203oai:depot.sorbonne.ae:20.500.12458/13072024-09-11T10:59:20Z
spellingShingle Hybrid encryption technique: Integrating the neural network with distortion techniques
Abu Zitar, Raed
title Hybrid encryption technique: Integrating the neural network with distortion techniques
title_full Hybrid encryption technique: Integrating the neural network with distortion techniques
title_fullStr Hybrid encryption technique: Integrating the neural network with distortion techniques
title_full_unstemmed Hybrid encryption technique: Integrating the neural network with distortion techniques
title_short Hybrid encryption technique: Integrating the neural network with distortion techniques
title_sort Hybrid encryption technique: Integrating the neural network with distortion techniques
url https://depot.sorbonne.ae/handle/20.500.12458/1307