期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2012
卷号：2
期号：3
出版社：S.S. Mishra
摘要：A Statistical database (SDB) is a database system that allows its users to retrieve aggregate statistics (e.g., sample mean and variance) for a subset of the entities represented in the database and prevents the collection of information on specific individuals. In the statistics community, there has been extensive research on the problem of securing SDBs against disclosure of confidential information. This is generally referred to as statistical disclosure control. Statistical disclosure control approaches suggested in the literature are classified into four general groups: conceptual, query restriction, output perturbation and data perturbation [1]. Conceptual approach provides a framework for better understanding and investigating the security problem of statistical database at the conceptual data model level. It does not provide a specific implementation procedure. The Query Restriction approach offers protection by either restricting the size of query set or controlling the overlap among successive queries. The Output Perturbation approach perturbs the answer to user queries while leaving the data in the database unchanged. The Data Perturbation approach introduces noise into the database and transforms it into another version. This paper primarily focuses on the data perturbation approaches.
