关键词: 医疗信息, 数据发布, 隐私保护, k-匿名, l-多样性

Abstract: With the rapid development of mobile health care, all kinds of medical institutions share personal medical data, but it still has the risk of privacy leak. This paper proposes a personalized entropy privacy protection model to protect the users' privacy with fine granularity based on k-anonymity and l-diversity model. To facilitate medical data sharing security, this model can reduce the leakage probabilities of sensitive information and medical intensive information by distinguishing the strong and weak sensitive attribute values to improve the sense of constraints. The experimental results show that the proposed method can not only enhance the accuracy of the data, but also reduce the execution time. In addition, it also can improve the quality of services and is more effective than existing methods.

Key words: medical information, data publishing, privacy preservation; k-anonymity, l-diversity