Mining privacy-preserving association rules using transaction hewer allocator and facile hash algorithm in...

Area of Science:

• Computer Science
• Data Security
• Cloud Computing

Background:

• Data-driven decision-making requires secure extraction of knowledge from distributed datasets.
• Privacy concerns arise when outsourcing data for tasks like frequent itemset mining.
• Balancing data sensitivity with insight delivery is a key challenge.

Purpose of the Study:

• To propose a novel multi-cloud privacy framework for secure frequent itemset mining.
• To enhance the efficiency and scalability of privacy-preserving data mining.
• To address privacy during data transmission and computation across distributed cloud platforms.

Main Methods:

• A multi-cloud privacy framework incorporating the Transaction Hewer and Allocator module and the Facile Hash Algorithm (FHA).
• Introduction of the Apriori with Tid Reduction (ATid) algorithm to improve scalability and computational efficiency.
• Performance evaluation using several datasets to compare with existing methods.

Main Results:

• The proposed framework demonstrates higher performance compared to existing methods.
• Encryption and decryption processes reduce computational time by up to 25%.
• Communication costs are reduced by approximately 15%, with improved scalability and reduced communication overhead.

Conclusions:

• The multi-cloud privacy framework effectively protects data during transmission and computation.
• The ATid algorithm significantly enhances scalability and operational efficiency in frequent itemset mining.
• The proposed approach offers a secure, efficient, and scalable solution for distributed data mining.