Date: Friday June 5, 2020

Time:  2:00 pm – 3:30pm

 

With the recent advances in Data Analytics  and  Machine  Learning,  organizations are becoming more and more interested in utilizing these techniques to generate insights from the data they have.  But the biggest hurdle, especially for those organizations who collect private data is that it becomes very difficult to share their data with data analysts without compromising the privacy of the data.  In 2006, Cynthia Dwork et al.  came up with something called Differential Privacy.  What this essentially does is that it makes sure that the answers to the queries of the data analyst does  not  compromise  the  privacy  of  any  of  the  participants  of  the  data  set.   Even though this seems very promising, it still poses a lot of burden on data analysts to understand Differential Privacy and manage privacy budgets accordingly.  Moreover, this also doesn’t give any accuracy guarantees to the data analyst.  Keeping this in mind, Chang Ge et al.  introduced a novel system called APEx in May 2019 which allows data analysts to run sequence of queries keeping privacy and accuracy in place. Change Ge et al.  in their work implemented APEx (Accuracy-Aware Differentially Private Data Exploration) for only one table in the database.  As we know that in real-world, relational databases never contain all of the data in only one table as it violates the database normalization concepts.  So, in order to test APEx on real-world scenarios, in this research it is extended and evaluated on multiple table queries.  Also, various other extensions/experiments to the original version of APEx are done.

 

Keywords: Differential Privacy, APEx, Privacy Preserving SQL Queries

Internal Reader: Dr. Alhadidi, Dima

External Reader: Dr. Razavi-Far, Roozbeh

Advisor: Dr. Saeed, Samet

Chair: Dr. Moradian Zadeh, Pooya

 

 

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca