A Privacy Protection Evaluation Framework for Anonymous Published Data
Zhiying Geng, Wanbang Qiao, Hongbo Liu · 2025
Although data privacy protection has drawn significant attention in recent years, there is still a lack of a unified method for efficient evaluation of privacy protection. In this study, we introduce a privacy protection evaluation framework leveraging a new indicator fusion method to assess the privacy protection effectiveness of published data. The proposed framework integrates multiple evaluation metrics, enabling a comprehensive and systematic assessment of data privacy. By conducting a thorough evaluation of the dataset, the framework provides crucial support for the optimization and improvement of subsequent data protection strategies. Experimental results demonstrate that our framework effectively quantifies the privacy protection effects across different scenarios and outperforms the way with single metrics.