Privacy-preserving data mining in peer to peer networks

Hussain, I; Irakleous, M; Siddiqi, MA; Saraee, MH

Abstract

In recent years, privacy-preserving data mining has been studied extensively, due to the wide increase of sensitive information on the internet. A number of algorithms and procedures have been designed, some of which are yet to be implemented, but a few of them are actually employed in the form of software systems to preserve the privacy of users, and the content in peer-to-peer networks. Privacy issues are becoming widely recognized when using peer-to-peer networks. In this paper, we provide a review of the privacy-preserving data mining techniques used in order to overcome privacy issues.
We discuss methods of sanitization, data distortion, data hiding, cryptography and the data mining algorithm KDEC. Further discussion involves data transfer using proxy techniques, creating social communities among peer-to-peer users forming trusted peers. These techniques have shown to administer the issue of preserving data however show lack of scalability and performance. We design a framework to perform a comparison study on the techniques shown above and present the results with some recommendations of how we think the issues could be unraveled.

Citation

Hussain, I., Irakleous, M., Siddiqi, M., & Saraee, M. (2010). Privacy-preserving data mining in peer to peer networks. In proceedings from the Annual International Conference on Data Analysis, Data Quality and Metadata Management. GSTF

• Start Date: Jun 14, 2010
• End Date: Jun 15, 2010
• Publication Date: Jan 1, 2010
• Deposit Date: Oct 27, 2011
• Publicly Available Date: Oct 27, 2011
• Book Title: proceedings from the Annual International Conference on Data Analysis, Data Quality and Metadata Management
• Related Public URLs: http://dl4.globalstf.org/?page=shop.browse&category_id=10&option=com_virtuemart&Itemid=1&vmcchk=1&Itemid=4
• Additional Information: Event Type : Conference