摘要
由于社交网络图结构的动态变化特性,需要采用有效的动态隐私保护方法。针对现有动态数据发布隐私保护方法中存在的攻击者背景知识单一、对图结构动态变化适应性较低等问题,提出基于聚类的动态图发布隐私保护方法。分析表明,该方法能抵御多种背景知识攻击,同时对社交网络图结构动态变化具有较好的适应性。
Due to the dynamic characteristics of the social network graph structure, an effective dynamic privacy preserving method is needed. To solve the problems of the existing dynamic privacy preservation methods, such as attacker's too little background knowledge and the low adaptability to the dynamic characteristics of graph structure, a clustering-based dynamic privacy preservation method is provided. The analysis shows that the proposed method can resist many kinds of background knowledge attacks and has good adaptability to the dynamic characteristics of the social network graph structure.
出处
《通信学报》
EI
CSCD
北大核心
2015年第S1期126-130,共5页
Journal on Communications
基金
国家自然科学基金资助项目(61173017)
工业和信息化部通信软科学基金资助项目(2014-R-42
2015-R-29)
信息网络安全公安部重点实验室开放课题基金资助项目(C14613)~~
关键词
动态社交网络
隐私保护
聚类
信息损失度
隐匿率
dynamic social networks
privacy preserving
clustering
information loss degree
anonymization rate
