Security of statistical databases compromise through attribute correlational modeling

Abstract

Statistical databases seek to provide accurate aggregate information to legitimate users, while protecting the confidentiality of individuals' information. This study develops, defines, and applies a statistical technique for the compromise of confidential information in a statistical database. Attribute Correlational Modeling (ACM) recognizes that the information contained in a statistical database represents real world statistical phenomena. As such, ACM utilizes the correlational behavior existing among the database attributes in order to compromise confidential information. The technique is applied to the 1980 U.S. Census Database and is found to be effective as a compromise tool. The contribution of the study is additional knowledge of the degree of security of confidential statistical databases. Knowledge of additional threats to security may lead to the eventual ability to identify high privacy risk databases, and possibly to reduce that degree of risk.