Loading...

Preserving Data Utility in Applying Differential Privacy on Correlated Data

Mohammadi, Ahmad | 2023

49 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56281 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Jalili, Rasoul
  7. Abstract:
  8. Differential privacy provides a powerful definition for protecting data privacy by adding noise. Differential privacy mechanisms add noise to the responses of queries made to a database. Differential privacy challenges the learning of useful information from a dataset without leaking any information about the individuals present in that dataset. However, studies have shown that these mechanisms make assumptions about the data that, if not met, can lead to privacy leaks. One of these assumptions is the lack of correlation between data. If an attacker is aware of the correlation between data, common mechanisms cannot guarantee differential privacy.This thesis proposes a solution for adding noise to the responses of queries sent to users despite the correlation between data. The solution consists of an algorithm for adding noise and a mechanism that, while preserving differential privacy and limiting its leakage to the differential privacy budget, also considers data correlation. The main advantage of the proposed solution is the preservation of the usefulness of the data while maintaining privacy for locally correlated data and reducing the intensity of data correlation.In addition to implementing the proposed mechanism in this thesis, three evaluations were performed to demonstrate the level of usefulness, reduction in data correlation, and resistance to correlation attacks, and the results were compared with a comprehensive random response mechanism
  9. Keywords:
  10. Differential Privacy ; Data Utility ; Correlated Data ; Privacy Preserving ; Correlation Attack ; Encountering

 Digital Object List

 Bookmark

No TOC