Scholarlink

<p>Sensitive data about the person cannot be disclosed without using privacy preservation procedures. One privacy-preserving method is Privacy Preserving Data Publishing (PPDP). The main obstacles, however, are decreased data loss and improved security. The privacy of the patients is proposed in this research using a unique method based on the ARFO-HBA (Adaptive Red Fox Optimization using Heap Bucketization Anonymity) model. ARFO algorithm uses average equivalence values and generalized information loss to calculate fitness values and generate keys for each sensitive property. Additionally, ARFO is used during the anatomization process to provide an additional layer of security for the database. Additionally, ARFO and HBA are combined to create the suggested ARFO-HBA model. In this case, the secret key generation process follows the objective measurements using the proposed ARFO algorithm. The utility loss in the patient dataset has been determined using the standardized certainty penalty and KL-divergence. According to experimental findings, ARFO-HBA performs much better than current models in terms of strong privacy with little value loss. Base knowledge attacks, quasi-id attacks, member attacks, non-member attacks, member attacks with biometric correlation attacks, etc., are not considered by the ARFO-HBA model.</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

ARFO-HBA: An Adaptive Red Fox Optimization Framework with Heap-Based Bucketization for Privacy-Preserving Data Publishing

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • S. Harihara Gopalan,
  • V. Vignesh,
  • D. Sivaganesan,
  • S. S. Sivaraju

摘要

Sensitive data about the person cannot be disclosed without using privacy preservation procedures. One privacy-preserving method is Privacy Preserving Data Publishing (PPDP). The main obstacles, however, are decreased data loss and improved security. The privacy of the patients is proposed in this research using a unique method based on the ARFO-HBA (Adaptive Red Fox Optimization using Heap Bucketization Anonymity) model. ARFO algorithm uses average equivalence values and generalized information loss to calculate fitness values and generate keys for each sensitive property. Additionally, ARFO is used during the anatomization process to provide an additional layer of security for the database. Additionally, ARFO and HBA are combined to create the suggested ARFO-HBA model. In this case, the secret key generation process follows the objective measurements using the proposed ARFO algorithm. The utility loss in the patient dataset has been determined using the standardized certainty penalty and KL-divergence. According to experimental findings, ARFO-HBA performs much better than current models in terms of strong privacy with little value loss. Base knowledge attacks, quasi-id attacks, member attacks, non-member attacks, member attacks with biometric correlation attacks, etc., are not considered by the ARFO-HBA model.