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), 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.