Secure big data sharing with hybrid encryption and deep learning

Securing and efficiently sharing large-scale data is a significant challenge, particularly in blockchain environments where ensuring data integrity and access control is crucial. This study introduces an innovative security framework that combines attribute-based and identity-based encryption (IABHE...

Full description

Saved in:
Bibliographic Details
Published in:Journal of King Saud University. Computer and information sciences Vol. 37; no. 8; pp. 216 - 29
Main Authors: Siyal, Reshma, Long, Jun, Khan, Sajid Ullah, Ayouni, Sarra, Maddeh, Mohamed
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 01.10.2025
Springer Nature B.V
Springer
Subjects:
Access control
Accuracy
Algorithms
Attack detection
Big Data
Blockchain
Blockchain security
Collaboration
Computer Imaging
Computer Science
Confidentiality
Cryptography
Data encryption
Data exchange
Data integrity
Database Management
Datasets
Deep learning
Deep stacked autoencoder
Efficiency
Encryption
Feature selection
Information sharing
Integrity
Machine Learning
Multiple data security
Neural networks
Original Paper
Pattern Recognition and Graphics
Performance evaluation
Privacy
Real time
Relief method
Security
Siamese convolutional neural network
Software Engineering/Programming and Operating Systems
Standard scores
Systems and Data Security
Theory of Computation
Threats
Vision
Attack detection
Blockchain security
Deep stacked autoencoder
Z-score normalization
Siamese convolutional neural network
Multiple data security
Relief method
ISSN:1319-1578, 2213-1248, 1319-1578
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Securing and efficiently sharing large-scale data is a significant challenge, particularly in blockchain environments where ensuring data integrity and access control is crucial. This study introduces an innovative security framework that combines attribute-based and identity-based encryption (IABHE), Honey Encryption, and a deep-learning-based attack detection system (SConvA-Net). The proposed model improves privacy, security, and trust in decentralized networks by employing an advanced encryption mechanism (IABHE + Honey Encryption) that provides fine-grained access control and improves resilience against cryptographic attacks. Furthermore, the SConvA-Net model enhances threat detection accuracy while minimizing false positives. By integrating these technologies, the framework reinforces blockchain-based data-sharing by ensuring confidentiality, authentication, and integrity. The performance evaluations indicate that the proposed approach outperforms conventional security methods in terms of encryption efficiency, cyber threat detection, and scalability. This study presents a robust, adaptable, and intelligent security solution for securing big data in blockchain ecosystems.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1319-1578
2213-1248
1319-1578
DOI:10.1007/s44443-025-00093-4