Authors:
Fatemeh Amiri
1
;
Gerald Quirchmayr
1
and
Peter Kieseberg
2
Affiliations:
1
University of Vienna, Vienna, Department of Computer Science, Austria, SBA Research Institue, Vienna and Austria
;
2
St. Poelten University of Applied Sciences, St. Poelten and Austria
Keyword(s):
Privacy-preserving, E-business, Big Data, Data Mining, Machine Learning.
Related
Ontology
Subjects/Areas/Topics:
Data and Application Security and Privacy
;
Data Protection
;
Database Security and Privacy
;
Information and Systems Security
;
Information Assurance
;
Information Hiding
;
Network Security
;
Privacy
;
Privacy Enhancing Technologies
;
Security and Privacy for Big Data
;
Security in Information Systems
;
Wireless Network Security
Abstract:
This paper aims at identifying and presenting useful solutions to close the privacy gaps in some definite data mining tasks with three primary goals. The overarching aim is to keep efficiency and accuracy of data mining tasks that handle the operations while trying to improve privacy. Specifically, we demonstrate that a machine learning methodology is an appropriate choice to preserve privacy in big data. As core contribution we propose a model consisting of several representative efficient methods for privacy-preserving computations that can be used to support data mining. The planned outcomes and contributions of this paper will be a set of improved methods for privacy-preserving soft-computing based clustering in distributed environments for e-business applications. The proposed model demonstrates that soft computing methods can lead to novel results not only to promote the privacy protection, but also for retaining performance and accuracy of regular operations, especially in onl
ine business applications.
(More)