Rating: Privacy Preservation for Multiple Attributes with Different Sensitivity Requirements

Liu, Jinfei; Luo, Jun; Huang, Joshua Zhexue

doi:10.1109/icdmw.2011.144

Cited by 39 publications

(46 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aiming to protect privacy information with multiple sensitive attributes, Yang Xiaochun [9] proposed a multiple sensitive attributes technology based on multi-dimensions buckets and described 3 corresponding algorithms according to greed method. Document [10] proposes an algorithm to classify multiple sensitive attributes which is to satisfy privacy protection by assign different sensitivity coefficients to different sensitive attributes. Document [11] proposes (k, l) module which assigns every degree of anonymity and the diversity of privacy attribute values of data items and achieves degree of anonymity and diversity with personalization.…”

Section: Introductionmentioning

confidence: 99%

A privacy protection algorithm based on hierarchical multiple sensitive attributes allowed by least mean square criterion

Cui¹,

Yang²,

Meng³

et al. 2016

Proceedings of the 2nd International Conference on Electronics, Network and Computer Engineering (ICENCE 2016)

View full text Add to dashboard Cite

Abstract. Based on L-diversity multiple sensitive modules, a hierarchical multiple sensitive attributes algorithm is proposed according to least mean square criterion ---L-LMSU (L-Least Mean Square Uniqueness). The algorithm makes a hierarchical strategy according to the frequencies of the whole attributes firstly. Beyond the hierarchical strategy, the algorithm could decrease the hidden loss because of non-uniform distribution of attributes when releasing privacy data in groups. Analysis and experiments show that L-LMSU is with linear time complexity and could improve the availability of released privacy data and time performances effectively.

show abstract

Section: Introductionmentioning

confidence: 99%

A privacy protection algorithm based on hierarchical multiple sensitive attributes allowed by least mean square criterion

Cui¹,

Yang²,

Meng³

et al. 2016

Proceedings of the 2nd International Conference on Electronics, Network and Computer Engineering (ICENCE 2016)

View full text Add to dashboard Cite

show abstract

“…As a part of this study various techniques have been identified and studied that could be used to preserve the user"s data sensitivity. The techniques namely Anonymization [6,7,8], Perturbation [9], Blocking based approach [10], Cryptographic techniques [11], Condensation approach [12,13] have been studied. Each of these techniques had come up with their own advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

A Study of Correlation Impact on Privacy Preserving Data Mining

Hyma¹,

Reddy²,

Damodaram³

2015

IJCA

View full text Add to dashboard Cite

Data sharing is obvious in present day scenario of digital world, and when data is being shared among various application areas the sensitive data of the individuals is disclosed to the public. An evident awareness about this privacy violation has been created among the people now when compared to the earlier days and they are also showing a real concern towards their privacy in the technology enabled digital world. At one end several studies have been proved that privacy is a primary concern and also suggesting not to disclose too much of individual information, but at the other end people are disclosing their personal information knowingly or unknowingly through online surveys, social networks, online shopping sites, e-commerce, government agencies etc. This information sharing is obvious and it can"t be unavoidable. Consequently several techniques have been proposed to protect privacy of the individual disclosed information, but still there is an immense need of new privacy preserving techniques that can equally accommodate with the proportionate expansion of the digital data. Existing privacy techniques applied on the data set assuming all the records are independently sampled, where as in the real world data set the correlations among the records is obvious and needs to be studied to achieve accurate privacy protection. This paper provides an overview of the development of privacy preserving models and the further enhancements to be carried out to accommodate with the diverse privacy requirements and data utilization along with the correlation study.

show abstract

“…Perturbation of data is a very easy and effective method for protecting sensitive information of the data from unauthorized users. This approach of perturbation is discussed in [3].there are two types of data perturbation for protecting data namely [4]: 1. Probability distribution approach (or) Data Swapping: This approach takes the data and replaces it from the same distribution sample or from the distribution itself.…”

Section: A Data Perturbationmentioning

confidence: 99%