Abstract
In this era of data-driven decision-making, it is important to securely and efficiently extract knowledge from distributed datasets. However, in outsourced data for tasks like frequent itemset mining, privacy is an important issue. The difficulty is to secure sensitive data while delivering the insights of the data. First, this paper proposes a new multi-cloud approach to preserve privacy, which includes two main components, named the Transaction Hewer and Allocator module and the Facile Hash Algorithm (FHA), in extracting the frequent itemset. All these components work together to protect the privacy of the data, wherever it is, during the transmission phase or the computation phase, even if it is raw data or processed data, on the different distributed cloud platforms. The complexities involved in the mining of frequent itemsets led us to introduce the Apriori with Tid Reduction (ATid) algorithm considering scalability and computational operational improvements to the mining process due to the Tid Reduction concept. We conduct performance evaluation on several datasets and show that our proposed framework achieves higher performance than existing methods, and encryption and decryption processes reduce the computational time by up to 25 % compared to the best alternative. It also exhibits approximately 15 % reduction in communication costs and displays scalability with the growing number of transactions, compared to the state-of-the-art evaluation metrics that indicate improved communication overhead.•Introduces a multi-cloud privacy framework with Facile Hash Algorithm and Transaction Hewer and Allocator.•Enhances scalability using ATid algorithm with Tid Reduction.