光华讲坛——社会名流与企业家论坛第2910期
主讲人：新墨西哥州立大學计算机科学系 曹会萍博士
主 题：Anonymizing social networks for individuals’ private or sensitive information.
主持人：经济信息工程学院 李庆教授
时 间：2013年5月27日（星期一） 上午：11:00
地 点：柳林校区经世楼C308
主 办：经济信息工程学院 科研处
主讲人介绍：
Huiping Cao, Assistant Professor in Computer Science at New Mexico State University;曹会萍，新墨西哥州立大學计算机科学系，助理教授；Journal of Data Semantics, Member of Editorial Board （编辑）。 Research interests include Data mining and Databases (in particular data integration).现在研究方向是数据挖掘和数据库（主要是数据集成）。She has published articles in premium data mining venues (e.g., KDD, TKDE, SDM，ICDM) and database venues (e.g., VLDB Journal, CIKM, EDBT).
讲座内容介绍：
本讲分为两个部分，第一个部分为学术交流部分，第二个部分为新墨西哥州立大學留学项目介绍部分，希望申请到美国学习的同学欢迎参加。
Online social networks, when published, provide a lot of opportunities to study dyadic ties between individuals in these networks. A big issue in publishing social networks is that we may expose individuals’ private or sensitive information. We study the problem of anonymizing social networks to prevent individual identifications, which use both structural (node degrees) and textual (edge labels) information in social networks. We introduce the concept of Structural and Textual (ST)-equivalence of individuals at two levels (strict and loose), and formally define the problem as Structure and Text aware K-anonymity of social networks (STK- Anonymity). In an STK-anonymized network, each individual is ST-equivalent to at least K-1 other nodes. The major challenge in achieving STK-Anonymity comes from the correlation of edge labels, which causes the propagation of edge anonymization. To address the challenge, we present a two-phase approach. In particular, a set-enumeration tree based approach and three pruning strategies are introduced in the second phase to avoid the propagation problem during anonymization. Experimental results on both real and synthetic datasets are presented to show the effectiveness and efficiency of our approaches.
