Scholarlink

<p>Sensitive data protection is a key issue in the context of Business Intelligence (BI), especially considering the increasing emergence of outsourcing computing over cloud. This paper presents an AI-driven automated solution designed to conceal sensitive data while maintaining its integrity for analytical purposes. We developed an anonymization pipeline that applies technologies such as pseudonymization and data masking, supported by machine learning for sensitive data detection. Our experiments demonstrate that anonymized data retains its analytical value with minimal impact on performance and accuracy, providing a solid foundation for secure and efficient BI outsourcing computing over cloud.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-driven anonymization for secure and privacy-preserving business intelligence cloud migration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月15日

查看全文
  • Najia Khouibiri,
  • Yousef Farhaoui,
  • Ahmad El Allaoui

摘要

Sensitive data protection is a key issue in the context of Business Intelligence (BI), especially considering the increasing emergence of outsourcing computing over cloud. This paper presents an AI-driven automated solution designed to conceal sensitive data while maintaining its integrity for analytical purposes. We developed an anonymization pipeline that applies technologies such as pseudonymization and data masking, supported by machine learning for sensitive data detection. Our experiments demonstrate that anonymized data retains its analytical value with minimal impact on performance and accuracy, providing a solid foundation for secure and efficient BI outsourcing computing over cloud.