Over the past few years, much has been written about the privacy risks inherent in data de-identification.1 Differential Privacy is a technology that enables researchers and analysts to extract useful answers from databases containing personal information and, at the same time, offers strong individual privacy protections. This seemingly contradictory outcome is achieved by introducing relatively small inaccuracies in the answers provided by the system. These inaccuracies are large enough that they protect privacy, but small enough that the answers provided to analysts and researchers are still useful. This whitepaper provides a non-technical description of how Differential Privacy works.
CITATION STYLE
五十嵐大, & 高橋克巳. (2012). 注目のプライバシーDifferential Privacy. コンピュータ・ソフトウェア, 29(4), 40–49.
Mendeley helps you to discover research relevant for your work.