期刊
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
卷 33, 期 2, 页码 331-343出版社
IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2019.2931903
关键词
Large scale graph publication; privacy preserving; graph decomposition; community detection
类别
资金
- National Key Research and Development Program of China [2016QY02D0302]
- National Natural Science Foundation of China (NSFC) [61472148]
The paper introduces a new k-decomposition algorithm and an information loss matrix designed for utility measurement in massively large graph datasets. Additionally, a novel privacy preserving framework is proposed to seamlessly integrate with graph storage, anonymization, query processing, and analysis.
The need to efficiently store and query large scale graph datasets is evident in the growing number of data-intensive applications, particularly to maximize the mining of intelligence from these data (e.g., to inform decision making). However, directly releasing graph dataset for analysis may leak sensitive information of an individual even if the graph is anonymized, as demonstrated by the re-identification attacks on the DBpedia datasets. A key challenge in the design of graph sanitization methods is scalability, as existing execution models generally have significant memory requirements. In this paper, we propose a novel k-decomposition algorithm and define a new information loss matrix designed for utility measurement in massively large graph datasets. We also propose a novel privacy preserving framework that can be seamlessly integrated with graph storage, anonymization, query processing, and analysis. Our experimental studies show that the proposed solution achieves privacy-preserving, utility, and efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据