Research on Privacy Preserving Data Mining Based on Randomized Response
Liu Xiao-ping, Jianfeng Li, Haina Song · 2020
Data mining has played an active role in some deep-level applications, but at the same time, it also brings many problems in information security and privacy protection. The association rule mining algorithm based on randomized response (RR) protects private information to a certain extent. However, because all the disturbed data in the data interference strategy based on randomized response are directly related to the real original data, the effect of privacy protection is not obvious. Aiming at this problem, this paper proposes a more effective privacy protection method in association rule mining. Based on the existing association rule mining model, a suitable perturbation strategy is designed to reduce the interference between the perturbed data and the original data. Relevance, without affecting the accuracy of mining, further enhance the degree of privacy protection of the mechanism.