Semantically Secure Classifiers for Privacy Preserving Data Mining

2018 ◽  
pp. 66-95
Author(s):  
Sumana M. ◽  
Hareesha K. S. ◽  
Sampath Kumar
Keyword(s):  
Data Mining ◽  
Model Building ◽  
Computation Time ◽  
Privacy Preserving ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Intermediate Data ◽  
Secure Protocols ◽  
Mean And Variance ◽  
Probabilistic Property

Essential predictions are to be made by the parties distributed at multiple locations. However, in the process of building a model, perceptive data is not to be revealed. Maintaining the privacy of such data is a foremost concern. Earlier approaches developed for classification and prediction are proven not to be secure enough and the performance is affected. This chapter focuses on the secure construction of commonly used classifiers. The computations performed during model building are proved to be semantically secure. The homomorphism and probabilistic property of Paillier is used to perform secure product, mean, and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost. It is also proved that proposed privacy preserving classifiers perform significantly better than the base classifiers.

Semantically Secure Classifiers for Privacy Preserving Data Mining

2021 ◽  
pp. 1066-1095
Author(s):  
Sumana M. ◽  
Hareesha K. S. ◽  
Sampath Kumar
Keyword(s):  
Data Mining ◽  
Model Building ◽  
Computation Time ◽  
Privacy Preserving ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Intermediate Data ◽  
Secure Protocols ◽  
Mean And Variance ◽  
Probabilistic Property

Essential predictions are to be made by the parties distributed at multiple locations. However, in the process of building a model, perceptive data is not to be revealed. Maintaining the privacy of such data is a foremost concern. Earlier approaches developed for classification and prediction are proven not to be secure enough and the performance is affected. This chapter focuses on the secure construction of commonly used classifiers. The computations performed during model building are proved to be semantically secure. The homomorphism and probabilistic property of Paillier is used to perform secure product, mean, and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost. It is also proved that proposed privacy preserving classifiers perform significantly better than the base classifiers.

Accurate Classification Models for Distributed Mining of Privately Preserved Data

2016 ◽  
Vol 10 (4) ◽  
pp. 58-73 ◽  
Author(s):  
Sumana M. ◽  
Hareesha K.S.
Keyword(s):  
Privacy Preservation ◽  
Computation Time ◽  
Privacy Preserving ◽  
Data Reconstruction ◽  
Sensitive Data ◽  
Intermediate Data ◽  
Secure Protocols ◽  
Mean And Variance ◽  
Mining Work ◽  
Probabilistic Property

Data maintained at various sectors, needs to be mined to derive useful inferences. Larger part of the data is sensitive and not to be revealed while mining. Current methods perform privacy preservation classification either by randomizing, perturbing or anonymizing the data during mining. These forms of privacy preserving mining work well for data centralized at a single site. Moreover the amount of information hidden during mining is not sufficient. When perturbation approaches are used, data reconstruction is a major challenge. This paper aims at modeling classifiers for data distributed across various sites with respect to the same instances. The homomorphic and probabilistic property of Paillier is used to perform secure product, mean and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost.

Accurate Classification Models for Distributed Mining of Privately Preserved Data

2019 ◽  
pp. 462-478
Author(s):  
Sumana M. ◽  
Hareesha K. S.
Keyword(s):  
Privacy Preservation ◽  
Computation Time ◽  
Privacy Preserving ◽  
Classification Models ◽  
Sensitive Data ◽  
Intermediate Data ◽  
Secure Protocols ◽  
Mean And Variance ◽  
Mining Work ◽  
Probabilistic Property

Data maintained at various sectors, needs to be mined to derive useful inferences. Larger part of the data is sensitive and not to be revealed while mining. Current methods perform privacy preservation classification either by randomizing, perturbing or anonymizing the data during mining. These forms of privacy preserving mining work well for data centralized at a single site. Moreover the amount of information hidden during mining is not sufficient. When perturbation approaches are used, data reconstruction is a major challenge. This paper aims at modeling classifiers for data distributed across various sites with respect to the same instances. The homomorphic and probabilistic property of Paillier is used to perform secure product, mean and variance calculations. The secure computations are performed without any intermediate data or the sensitive data at multiple sites being revealed. It is observed that the accuracy of the classifiers modeled is almost equivalent to the non-privacy preserving classifiers. Secure protocols require reduced computation time and communication cost.

Privacy-Preserving Data Mining and the Need for Confluence of Research and Practice

2008 ◽  
pp. 2402-2420
Author(s):  
Lixin Fu ◽  
Hamid Nemati ◽  
Fereidoon Sadri
Keyword(s):  
Data Mining ◽  
Research Agenda ◽  
Information Technologies ◽  
Privacy Preserving ◽  
Theory And Practice ◽  
Clear Understanding ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Research And Practice ◽  
Rapid Pace

Privacy-preserving data mining (PPDM) refers to data mining techniques developed to protect sensitive data while allowing useful information to be discovered from the data. In this article, we review PPDM and present a broad survey of related issues, techniques, measures, applications, and regulation guidelines. We observe that the rapid pace of change in information technologies available to sustain PPDM has created a gap between theory and practice. We posit that without a clear understanding of the practice, this gap will be widening which, ultimately, will be detrimental to the field. We conclude by proposing a comprehensive research agenda intended to bridge the gap relevant to practice and as a reference basis for the future related legislation activities.

Privacy-Preserving Data Mining and the Need for Confluence of Research and Practice

2011 ◽  
pp. 60-78
Author(s):  
Lixin Fu ◽  
Hamid Nemati ◽  
Fereidoon Sadri
Keyword(s):  
Data Mining ◽  
Research Agenda ◽  
Information Technologies ◽  
Privacy Preserving ◽  
Theory And Practice ◽  
Clear Understanding ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Research And Practice ◽  
Rapid Pace

Privacy-Preserving Data Mining (PPDM) refers to data mining techniques developed to protect sensitive data while allowing useful information to be discovered from the data. In this chapter the review PPDM and present a broad survey of related issues, techniques, measures, applications, and regulation guidelines. The authors observe that the rapid pace of change in information technologies available to sustain PPDM has created a gap between theory and practice. They posit that without a clear understanding of the practice, this gap will be widening, which, ultimately will be detrimental to the field. They conclude by proposing a comprehensive research agenda intended to bridge the gap relevant to practice and as a reference basis for the future related legislation activities.

Web based Privacy Disclosure Threats and Control Techniques

2016 ◽  
pp. 334-341
Author(s):  
Tithi Hunka ◽  
Sital Dash ◽  
Prasant Kumar Pattnaik
Keyword(s):  
Data Mining ◽  
Privacy Preserving ◽  
Extensive Study ◽  
Security And Privacy ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Web Based ◽  
Data Mining Techniques ◽  
The Public ◽  
And Control

Due to advancement of internet technologies, web based applications are gaining popularity day by day. Many organizations maintain large volumes of web site based data about individuals that may carry information that cannot be revealed to the public or researchers. While web-based applications are becoming increasingly pervasive by nature, they also present new security and privacy challenges. However, privacy threats effects negatively on sensitive data and possibly leads to the leakage of confidential information. More ever, privacy preserving data mining techniques allow us to protect the sensitive data before it gets published to the public by changing the original micro-data format and contents. This chapter is intended to undertake an extensive study on some ramified disclosure threats to the privacy and PPDM (privacy preserving data mining) techniques as a unified solution to protect against threats.

scholarly journals Privacy Preserving Mining in Code Profiling Data

2018 ◽  
Vol 8 (5) ◽  
Author(s):  
Meenakshi Kathayat
Keyword(s):  
Data Mining ◽  
Software Engineering ◽  
Future Development ◽  
Data Privacy ◽  
Software Metrics ◽  
Privacy Preserving ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Encrypted Data

Privacy preserving data mining is an important issue nowadays for data mining. Since various organizations and people are generating sensitive data or information these days. They don’t want to share their sensitive data however that data can be useful for data mining purpose. So, due to privacy preserving mining that data can be mined usefully without harming the privacy of that data. Privacy can be preserved by applying encryption on database which is to be mined because now the data is secure due to encryption. Code profiling is a field in software engineering where we can apply data mining to discover some knowledge so that it will be useful in future development of software. In this work we have applied privacy preserving mining in code profiling data such as software metrics of various codes. Results of data mining on actual and encrypted data are compared for accuracy. We have also analyzed the results of privacy preserving mining in code profiling data and found interesting results.

Privacy-Preserving Data Mining and the Need for Confluence of Research and Practice

2008 ◽  
pp. 3451-3469
Author(s):  
Lixin Fu ◽  
Hamid Nemati ◽  
Fereidoon Sadri
Keyword(s):  
Data Mining ◽  
Research Agenda ◽  
Information Technologies ◽  
Privacy Preserving ◽  
Theory And Practice ◽  
Clear Understanding ◽  
Sensitive Data ◽  
Privacy Preserving Data Mining ◽  
Research And Practice ◽  
Rapid Pace

Privacy-preserving data mining (PPDM) refers to data mining techniques developed to protect sensitive data while allowing useful information to be discovered from the data. In this article, we review PPDM and present a broad survey of related issues, techniques, measures, applications, and regulation guidelines. We observe that the rapid pace of change in information technologies available to sustain PPDM has created a gap between theory and practice. We posit that without a clear understanding of the practice, this gap will be widening which, ultimately, will be detrimental to the field. We conclude by proposing a comprehensive research agenda intended to bridge the gap relevant to practice and as a reference basis for the future related legislation activities.

Sign in / Sign up

Export Citation Format

Share Document