Privacy and Confidentiality in an e-Commerce World: Data Mining, Data Warehousing, Matching and Disclosure Limitation

摘要

The growing expanse of e-commerce and the widespread availability of onlinedatabases raise many fears regarding loss of privacy and many statisticalchallenges. Even with encryption and other nominal forms of protection forindividual databases, we still need to protect against the violation of privacythrough linkages across multiple databases. These issues parallel those thathave arisen and received some attention in the context of homeland security.Following the events of September 11, 2001, there has been heightened attentionin the United States and elsewhere to the use of multiple government andprivate databases for the identification of possible perpetrators of futureattacks, as well as an unprecedented expansion of federal government datamining activities, many involving databases containing personal information. Wepresent an overview of some proposals that have surfaced for the search ofmultiple databases which supposedly do not compromise possible pledges ofconfidentiality to the individuals whose data are included. We also exploretheir link to the related literature on privacy-preserving data mining. Inparticular, we focus on the matching problem across databases and the conceptof ``selective revelation'' and their confidentiality implications.