Authors:
Emmanouil Magkos
and
Vassilis Chrissikopoulos
Affiliation:
Ionian University, Greece
Keyword(s):
Data mining, Privacy, Security, Cryptography, Distributed systems.
Related
Ontology
Subjects/Areas/Topics:
Access Control
;
Artificial Intelligence
;
Data Engineering
;
Databases and Data Security
;
Databases and Datawarehouses
;
Distributed and Parallel Applications
;
Information and Systems Security
;
Internet Technology
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Soft Computing
;
Symbolic Systems
;
Web Information Systems and Technologies
;
Web Mining
;
Web Security and Privacy
Abstract:
A common fact for both businesses and physical entities is that sensitive, accurate information would be more easily diffused if adequate measures for protection were in place. This could also lead to higher quality data mining results, in a privacy preserving manner. Recent research has proved that it is possible to provide both privacy and accuracy assurances in a distributed computing scenario, where all participants may be mutually untrusted, without the presence of an unconditionally trusted third party. We believe that valuable knowledge can be borrowed from the vast body of literature on e-auction and e-voting systems, in order to be adapted to privacy preserving data mining systems in a distributed environment. These systems tend to balance well the efficiency and security criteria, because they need to be implementable in medium to large scale environments.