An Investigation of Data Privacy and Utility Using Machine Learning as a Gauge
“AN INVESTIGATION OF DATA PRIVACY AND
UTILITY USING MACHINE LEARNING AS A GAUGE”
Kato Mivule, D.Sc. Candidate, Computer Science
Bowie State University
Thursday, April 10, 2014 @ 3:30 – 4:45 PM, CSB - Room 210
Kato Mivule is a doctoral candidate in the Department of Computer Science
at The Bowie State University, advised by Dr. Claude Turner. His research
interests consist of data privacy and utility preservation, machine learning,
data mining, database systems, and multi-agent learning systems. His
current work includes investigating an optimal equilibrium between data
privacy and utility needs using machine learning classifiers as a gauge. He
got his Associates in Computer Information Systems from Longview
Community College, in Missouri, USA, and Bachelors in Computer Science
from the University of Missouri – Kansas City, USA.
Organizations that transact in large amounts of data have to comply with
federal laws to guarantee that the privacy of individuals and other sensitive
data is not compromised. However, during the data privacy process, data
loses its utility – a measure of how useful a privatized dataset is to the user
of that dataset. Researchers have noted that attaining an optimal balance
between data privacy and utility needs is an NP-hard challenge, thus
intractable. Therefore we present the classification error gauge (x-CEG)
model, a quantification approach that employs machine learning
classification to gauge data utility based on the classification error.
Additionally, we present SIED, an innovative conceptual framework that
takes a holistic approach to the data privacy and utility engineering process
by outlining the specifications, implementation, evaluation, and
dissemination phases in the data privacy process.
Contact Dr. Soo-Yeon Ji (firstname.lastname@example.org) if you have any question.