PRIVACY-PRESERVING DATA MINING TECHNIQUES IN CLOUD-BASED INFORMATION SYSTEMS

Abstract

With the exponential growth of cloud computing and data-driven decision-making, preserving privacy in data mining has become a pressing concern. Cloud-based Information Systems (CBIS) enable large-scale data storage and processing, but they also introduce security and privacy vulnerabilities, especially in multi-tenant and distributed environments. This study presents a comprehensive review of privacy-preserving data mining (PPDM) techniques suitable for CBIS. Emphasis is placed on methods such as differential privacy, homomorphic encryption, secure multi-party computation (SMPC), and data anonymization. Through comparative analysis and case-based evaluations, the paper outlines the trade-offs between utility and privacy, system efficiency, and implementation feasibility in cloud architectures. The findings highlight the need for hybrid and adaptive privacy models to ensure secure and trustworthy cloud computing ecosystems.