A hybrid machine learning model with self-improved optimization algorithm for trust and privacy preservation in cloud environment

Abstract

Abstract The rapid adoption of cloud-based data sharing is transforming collaboration across various sectors, yet ensuring trust and privacy in sensitive data remains a critical challenge. This paper presents a hybrid model aimed at enhancing data privacy and trust in cloud environments, specifically addressing concerns in healthcare and finance. The model combines k-anonymity for user privacy, an optimized Firefly algorithm for trust generation, and a Time-aware Modified Best Fit Decreasing (T-MBFD) algorithm to improve resource allocation efficiency. Key contributions include a comprehensive methodology that encompasses dataset selection, preprocessing, model training, and evaluation across multiple datasets, including healthcare, financial, and pandemic-related data. Experimental results demonstrate that the hybrid model achieves a precision score of approximately 90% and an accuracy of around 93% in financial datasets, significantly outperforming existing methods in both privacy preservation and computational efficiency. These findings emphasize the model’s effectiveness in securely facilitating data-driven collaboration in highly regulated domains, thus paving the way for practical applications that uphold individual privacy and data integrity in cloud-based environments.

Keywords

• Time-aware modified best fit decreasing (T-MBFD)
• Resource allocation
• Privacy preservation
• Trust generation
• State-of-the-art algorithms