Distributed Privacy Preserving Clustering via Homomorphic Secret Sharing and Its Application to (Vertically) Partitioned Spatio-Temporal Data

Cyber Crime ◽  
2013 ◽  
pp. 395-415 ◽  
Author(s):  
Can Brochmann Yildizli ◽  
Thomas Pedersen ◽  
Yucel Saygin ◽  
Erkay Savas ◽  
Albert Levi
Keyword(s):  
Data Mining ◽  
Real World ◽  
Privacy Preserving ◽  
Secure Multiparty Computation ◽  
Multiparty Computation ◽  
Privacy Preserving Data Mining ◽  
Computational Costs ◽  
Data Mining Algorithms ◽  
Spatio Temporal ◽  
Mining Algorithms

Recent concerns about privacy issues have motivated data mining researchers to develop methods for performing data mining while preserving the privacy of individuals. One approach to develop privacy preserving data mining algorithms is secure multiparty computation, which allows for privacy preserving data mining algorithms that do not trade accuracy for privacy. However, earlier methods suffer from very high communication and computational costs, making them infeasible to use in any real world scenario. Moreover, these algorithms have strict assumptions on the involved parties, assuming involved parties will not collude with each other. In this paper, the authors propose a new secure multiparty computation based k-means clustering algorithm that is both secure and efficient enough to be used in a real world scenario. Experiments based on realistic scenarios reveal that this protocol has lower communication costs and significantly lower computational costs.

Distributed Privacy Preserving Clustering via Homomorphic Secret Sharing and its Application to (Vertically) Partitioned Spatio-Temporal Data

2013 ◽  
pp. 45-65
Author(s):  
Can Brochmann Yildizli ◽  
Thomas Pedersen ◽  
Yucel Saygin ◽  
Erkay Savas ◽  
Albert Levi
Keyword(s):  
Data Mining ◽  
Real World ◽  
Privacy Preserving ◽  
Secure Multiparty Computation ◽  
Multiparty Computation ◽  
Privacy Preserving Data Mining ◽  
Computational Costs ◽  
Data Mining Algorithms ◽  
Spatio Temporal ◽  
Mining Algorithms

Recent concerns about privacy issues have motivated data mining researchers to develop methods for performing data mining while preserving the privacy of individuals. One approach to develop privacy preserving data mining algorithms is secure multiparty computation, which allows for privacy preserving data mining algorithms that do not trade accuracy for privacy. However, earlier methods suffer from very high communication and computational costs, making them infeasible to use in any real world scenario. Moreover, these algorithms have strict assumptions on the involved parties, assuming involved parties will not collude with each other. In this paper, the authors propose a new secure multiparty computation based k-means clustering algorithm that is both secure and efficient enough to be used in a real world scenario. Experiments based on realistic scenarios reveal that this protocol has lower communication costs and significantly lower computational costs.

Distributed Privacy Preserving Clustering via Homomorphic Secret Sharing and Its Application to (Vertically) Partitioned Spatio-Temporal Data

2011 ◽  
Vol 7 (1) ◽  
pp. 46-66 ◽  
Author(s):  
Can Brochmann Yildizli ◽  
Thomas Pedersen ◽  
Yucel Saygin ◽  
Erkay Savas ◽  
Albert Levi
Keyword(s):  
Data Mining ◽  
Real World ◽  
Clustering Algorithm ◽  
Privacy Preserving ◽  
Secure Multiparty Computation ◽  
Multiparty Computation ◽  
Privacy Preserving Data Mining ◽  
Computational Costs ◽  
Data Mining Algorithms ◽  
Mining Algorithms

Recent concerns about privacy issues have motivated data mining researchers to develop methods for performing data mining while preserving the privacy of individuals. One approach to develop privacy preserving data mining algorithms is secure multiparty computation, which allows for privacy preserving data mining algorithms that do not trade accuracy for privacy. However, earlier methods suffer from very high communication and computational costs, making them infeasible to use in any real world scenario. Moreover, these algorithms have strict assumptions on the involved parties, assuming involved parties will not collude with each other. In this paper, the authors propose a new secure multiparty computation based k-means clustering algorithm that is both secure and efficient enough to be used in a real world scenario. Experiments based on realistic scenarios reveal that this protocol has lower communication costs and significantly lower computational costs.

scholarly journals Privacy Preserving Data Mining

2021 ◽  
Author(s):  
Esma Ergüner Özkoç
Keyword(s):  
Data Mining ◽  
Data Privacy ◽  
Personal Data ◽  
Privacy Preserving ◽  
Privacy Preserving Data Mining ◽  
Data Mining Techniques ◽  
Data Mining Algorithms ◽  
Data Output ◽  
The Individual ◽  
Mining Algorithms

Data mining techniques provide benefits in many areas such as medicine, sports, marketing, signal processing as well as data and network security. However, although data mining techniques used in security subjects such as intrusion detection, biometric authentication, fraud and malware classification, “privacy” has become a serious problem, especially in data mining applications that involve the collection and sharing of personal data. For these reasons, the problem of protecting privacy in the context of data mining differs from traditional data privacy protection, as data mining can act as both a friend and foe. Chapter covers the previously developed privacy preserving data mining techniques in two parts: (i) techniques proposed for input data that will be subject to data mining and (ii) techniques suggested for processed data (output of the data mining algorithms). Also presents attacks against the privacy of data mining applications. The chapter conclude with a discussion of next-generation privacy-preserving data mining applications at both the individual and organizational levels.

Sensitive Items in Privacy Preserving — Association Rule Mining

2008 ◽  
Vol 07 (01) ◽  
pp. 31-35
Author(s):  
K. Duraiswamy ◽  
N. Maheswari
Keyword(s):  
Data Mining ◽  
Private Information ◽  
Association Rule ◽  
Association Rule Mining ◽  
Privacy Preserving ◽  
Data Input ◽  
Rule Mining ◽  
Privacy Preserving Data Mining ◽  
Data Mining Algorithms ◽  
Mining Algorithms

Privacy-preserving has recently been proposed in response to the concerns of preserving personal or sensible information derived from data-mining algorithms. For example, through data-mining, sensible information such as private information or patterns may be inferred from non-sensible information or unclassified data. As large repositories of data contain confidential rules that must be protected before published, association rule hiding becomes one of important privacy preserving data-mining problems. There have been two types of privacy concerning data-mining. Output privacy tries to hide the mining results by minimally altering the data. Input privacy tries to manipulate the data so that the mining result is not affected or minimally affected. For some applications certain sensitive predictive rules are hidden that contain given sensitive items. To identify the sensitive items an algorithm SENSITEM is proposed. The results of the work have been given.

Sign in / Sign up

Export Citation Format

Share Document