A robust introduction to the core ideas, history, and key applications of differential privacy-the gold standard of algorithmic privacy protection.

A robust introduction to the core ideas, history, and key applications of differential privacy-the gold standard of algorithmic privacy protection.

Differential privacy (DP) is an increasingly popular, though controversial, approach to protecting personal data. DP protects confidential data by introducing carefully calibrated random numbers, called statistical noise, when the data is used. Google, Apple, and Microsoft have all pushed the technology into their consumer offerings. In this book, Simson Garfinkel presents the underlying ideas of DP, and helps explain why DP is needed in today's information-rich environment, why it was used as the privacy protection mechanism for the 2020 census, and why it is so controversial in some communities.

When DP is used to create statistics, like the publications from the 2020 Census, the noise makes it impossible for someone to take that published statistic and access, with absolute certainty, the underlying confidential data from which the statistic was computed. When DP is used in a commercial application-for example, when advertisements are shown to users on the Internet-it limits the ability of someone observing those advertisements to make reliable inferences as to why a specific advertisement was selected for a specific recipient. The book also chronicles the history of DP and describes the key participants and its limitations. Along the way, the book also presents a short history of the US Census and other approaches for data protection such as de-identification and k-anonymity.