A Personalized Differential Privacy Protection Method for Repeated Queries
Senyou Li, Xinsheng Ji, Wei You · 2019
As the emergence and development of application requirements such as data analysis and data publication, how to prevent sensitive information from disclosure has become a great challenge. Traditional differential privacy providing the same level of privacy protection for all users has serious limitations. Moreover there is privacy flaw in dealing with repeat query attacks. In this paper, we propose a personalized differential privacy protection method for repeated queries, generating a new privacy protection specification according to the data privacy protection requirements, query user privilege and the number of same queries. The proposed differentiated privacy protection is achieved by adding random noise with different distribution characteristics to the query results. Simulation experiments show that the proposed method can solve the privacy leakage threat caused by repeated query attacks effectively, and can provide strong personalized differential privacy protection for multi-user aggregate queries in data analysis and data publication.