Title: Distributed and personalised social network privacy protection

Authors: Xiao-lin Zhang; Xiao-yu He; Fang-ming Yu; Li-xin Liu; Huan-xiang Zhang; Zhuo-lin Li

Addresses: School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China ' School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China ' School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China ' School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China ' School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China ' School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China

Abstract: Considering the privacy issues on social network, a variety of anonymous techniques have been proposed, but these techniques neglect some differences among individuals in their demand for privacy protection. With the development of internet technology, the number of social network individuals increases yearly, and network data are poised for a massive change in trends. Motivated by this, we specify three levels of privacy information for victim individuals and propose a personalised k-degree-m-label (PKDML) anonymity model. Furthermore, we design and implement a distributed and personalised k-degree-m-lable (DPKDML) anonymisation algorithm, which takes advantage of the 'vertex-centric' GraphX programming model to complete the entire anonymous process by multiple message passing and node value updating. Finally, we conduct experiments on real social network datasets to evaluate the DPKDML, The experimental results show that our methods may overcome the shortcomings of traditional methods in processing massive data, and reduce anonymous costs and increase data utility.

Keywords: social networks; privacy protection; distributed; personalised; GrapX.

DOI: 10.1504/IJHPCN.2019.097506

International Journal of High Performance Computing and Networking, 2019 Vol.13 No.2, pp.153 - 163

Received: 31 May 2017
Accepted: 28 Nov 2017
Published online: 25 Jan 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article