A Deep Cryptographic Framework for Securing the Healthcare Network from Penetration.

Area of Science:

• Computer Science
• Information Security
• Medical Imaging

Background:

• Conventional image embedding systems struggle with network security, risking unauthorized data access and misuse.
• Previous image security techniques often suffer from high execution times and performance limitations.

Purpose of the Study:

• To introduce a novel framework, Graph Convolutional-Based Twofish Security (GCbTS), for securing medical images.
• To address the challenges of performance and security in existing image security methods.

Main Methods:

• Utilized medical data from Kaggle, performing preprocessing to remove noise and computing hash values.
• Implemented a Graph Convolutional-Based Twofish Security (GCbTS) framework for encryption and decryption using generated keys.
• Incorporated hash value comparison for user identity verification.

Main Results:

• The GCbTS framework successfully encrypts and decrypts medical images, ensuring data integrity.
• Hash value comparison effectively verifies user identity, enhancing security protocols.
• The proposed model demonstrates improved effectiveness in picture privacy compared to existing methods.

Conclusions:

• The GCbTS framework offers a robust solution for securing medical images on networks.
• This approach enhances data privacy and mitigates risks of unauthorized access in healthcare.
• The study highlights the potential of graph convolutional networks and Twofish encryption for medical image security.