Differential privacy made easy

AITSAM, Muhammad (2023). Differential privacy made easy. In: 2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering. IEEE.

Full text not available from this repository.
Official URL: https://ieeexplore.ieee.org/document/10007322
Link to published version:: https://doi.org/10.1109/etecte55893.2022.10007322


Data privacy has been a significant issue for many decades. Several techniques have been developed to make sure individuals' privacy but still, the world has seen privacy failures. In 2006, Cynthia Dwork gave the idea of Differential Privacy which gave strong theoretical guarantees for data privacy. Many companies and research institutes developed differential privacy libraries, but in order to get differentially private results, users have to tune the privacy parameters. In this paper, we minimized these tunable parameters. The DP-framework is developed which compares the differentially private results of three Python based differential privacy libraries. We also introduced a new very simple DP library (GRAM - DP), so that people with no background in differential privacy can still secure the privacy of the individuals in the dataset while releasing statistical results in public.

Item Type: Book Section
Identification Number: https://doi.org/10.1109/etecte55893.2022.10007322
SWORD Depositor: Symplectic Elements
Depositing User: Symplectic Elements
Date Deposited: 31 Jan 2023 13:16
Last Modified: 11 Oct 2023 17:47
URI: https://shura.shu.ac.uk/id/eprint/31342

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics