Privacy-Preserving Data Publishing

Privacy preservation has become a major issue in many data analysis applications. When a data set is released to other parties for data analysis, privacy-preserving techniques are often required to reduce the possibility of identifying sensitive information about individuals. For example, in medical data, sensitive information can be the fact that a particular patient suffers from HIV. In spatial data, sensitive information can be a specific location of an individual. In web surfing data, the information that a user browses certain websites may be considered sensitive. Consider a dataset containing some sensitive information is to be released to the public. In order to protect sensitive information, the simplest solution is not to disclose the information. However, this would be an overkill since it will hinder the process of data analysis over the data from which we can find interesting patterns. Moreover, in some applications, the data must be disclosed under the government regulations. Alternatively, the data owner can first modify the data such that the modified data can guarantee privacy and, at the same time, the modified data retains sufficient utility and can be released to other parties safely. This process is usually called as privacy-preserving data publishing. In this monograph, we study how the data owner can modify the data and how the modified data can preserve privacy and protect sensitive information. Table of Contents: Introduction / Fundamental Concepts / One-Time Data Publishing / Multiple-Time Data Publishing / Graph Data / Other Data Types / Future Research Directions

Introduction.- Fundamental Concepts.- One-Time Data Publishing.- Multiple-Time Data Publishing.- Graph Data.- Other Data Types.- Future Research Directions.

Raymond Chi-Wing Wong received the B.Sc., M.Phil., and Ph.D. degrees in Computer Science and Engineering in the Chinese Univer[1]sity of Hong Kong (CUHK) in 2002, 2004 and 2008, respectively. He joined Computer Science and Engineering of the Hong Kong Uni[1]versity of Science and Technology as an Assistant Professor in 2008. During 2004-2005, he worked as a research and development assistant under an R&D project funded by ITF and a local company called Life[1]wood. He has published over 35 papers at major journals and confer[1]ences such as TODS, VLDBJ, TKDE, SIGKDD, VLDB, ICDE and ICDM. He has received over 20 awards. He served on the program committees of VLDB, CIKM, DASFAA, SDM and APWeb-WAIM, and refereed for a variety of journals. His research interests include database, data mining and security. Ada Wai-Chee Fu received her B.Sc degree in computer science in the Chinese University of Hong Kong in 1983, and both M.Sc. and Ph.D. degrees in Computer Science in Simon Fraser University of Canada in 1986, 1990, respectively. She worked at Bell Northern Research in Ottawa, Canada from 1989 to 1993 on a wide-area distributed database projects. She joined the Chinese University of Hong Kong in 1993. Her research interests include database systems and data mining.