Efficient and Secure Privacy Analysis for Medical Big Data Using TDES and MKSVM with Access Control in Cloud

Area of Science:

• Cloud Computing
• Big Data Security
• Information Technology

Background:

• Big Data and cloud computing are pivotal in modern IT services.
• Securing sensitive data in the cloud is challenging, especially with encryption.
• Cloud data deduplication and access control are crucial for big data storage.

Purpose of the Study:

• To dissect medical big data security using encryption and access control.
• To enhance the efficiency and effectiveness of cloud computing resources.
• To address challenges in cloud data deduplication for encrypted data.

Main Methods:

• Utilized Map-Reduce framework with Optimal Fuzzy C-means (OFCM) for data clustering.
• Employed a classification approach to differentiate sensitive and non-sensitive data for encryption.
• Implemented Triple DES (TDES) encryption and attribute-based access control for authentication.

Main Results:

• Clustered, classified, and encrypted medical big data in the cloud.
• Proposed optimization techniques to improve the security scheme's performance.
• Validated the approach through simulation, comparing results with existing methods.

Conclusions:

• The proposed method effectively enhances medical big data security in cloud environments.
• Integrating clustering, classification, and TDES encryption with access control improves data protection.
• The approach offers a robust solution for secure big data storage and processing in the cloud.