ULDP: A User-Centric Local Differential Privacy Optimization Method

Differential privacy methods have become increasingly popular in various applications in recent years. However, the task of enabling users to achieve efficient control over the privacy levels of their data is becoming increasingly complex and time-consuming. Further, attaining an acceptable equilibrium between preserving privacy and maintaining a high degree of data accuracy within datasets requires a profound comprehension of the complexities inherent in the data. In order to address these challenges, we propose the implementation of a user-centric local differential privacy (ULDP) model, which utilizes multi-criteria decision-making methodologies. The method we propose enables users or data owners to effortlessly manage and control the privacy settings of datasets according to their specific needs. Results from evaluating our proposed ULDP method demonstrate efficacy in optimally harmonizing the conflicting goals of data accuracy and data privacy preservation.