Differential Privacy
Regular price
$17.05 USD
Regular price
$28.42 USD
Sale price
$17.05 USD
Unit price
per
You save $11.37 USD (40%)
In stock — Ships within 1–2 business days
Format
Print Book
Currently viewing
Paperback
$17.05 USD
$28.42 USD
Secure CheckoutYour data is protected
Fast U.S. ShippingShips within 1–2 business days
Authentic Titles100% Genuine Books
AlbakiReads Editorial A grounded guide to the promises and trade-offs of differential privacy
A grounded guide to the promises and trade-offs of differential privacy
Differential Privacy explains a widely used approach to protecting confidential data: adding calibrated statistical noise to data outputs so that underlying personal information cannot be determined with absolute certainty. Simson L. Garfinkel places the method in the context of an information-rich environment, tracing its development, the people involved in its history, and the debates surrounding its use. The book also examines differential privacy’s role in protecting data from the 2020 US Census, alongside earlier or alternative approaches including de-identification and k-anonymity. Its attention to both applications and limitations frames differential privacy not simply as a technical mechanism, but as a contested practical choice in data governance.
Good fit for readers who enjoy
- Readers seeking an accessible introduction to privacy-preserving data methods
- Technology and security readers interested in how personal data is protected
- Those interested in the privacy debates around the 2020 US Census
Themes
Data privacyDifferential privacyStatistical noiseData governanceUS Census data protection
Based on publisher information and book metadata.
Book Overview A robust yet accessible introduction to the idea, history, and key applications of differential privacy--the gold standard of algorithmic...
A robust yet accessible introduction to the idea, 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 integrated the technology into their software, and the US Census Bureau used DP to protect data collected in the 2020 census. 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 protect confidential data, like an advertising profile based on the web pages you have viewed with a web browser, the noise makes it impossible for someone to take that profile and reverse engineer, with absolute certainty, the underlying confidential data on which the profile was computed. The book also chronicles the history of DP and describes the key participants and its limitations. Along the way, it also presents a short history of the US Census and other approaches for data protection such as de-identification and k-anonymity.
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 integrated the technology into their software, and the US Census Bureau used DP to protect data collected in the 2020 census. 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 protect confidential data, like an advertising profile based on the web pages you have viewed with a web browser, the noise makes it impossible for someone to take that profile and reverse engineer, with absolute certainty, the underlying confidential data on which the profile was computed. The book also chronicles the history of DP and describes the key participants and its limitations. Along the way, it also presents a short history of the US Census and other approaches for data protection such as de-identification and k-anonymity.
Book Details Format: Paperback | Pages: 244 | Language: English | Publisher: MIT PR | ISBN: 0262551659
FormatPaperback
Pages244
LanguageEnglish
ISBN0262551659
EAN9780262551656
PublisherMIT PR
Publication Date2025-03-25
AccessoriesNo Accessory
ConditionNew
Product TypeQUALITY PAPERBACK BOOKS
Weight0.45 Pounds
Length6.9 Inches
Width5.0 Inches
Height0.8 Inches
Shipping & Returns Fast, reliable shipping and easy returns on eligible items.
Most orders ship within 1–2 business days with fast, reliable U.S. delivery.
Eligible items can be returned within 30 days in line with our store return policy.
Why shop with AlbakiReads
Fresh Inventory from Major Publishers
Sourced through trusted book distributors, with fresh titles added regularly.
Secure Checkout
Your payment information is encrypted and protected every step of the way.
Fast U.S. Shipping
Most orders ship within 1–2 business days.
Books for Every Kind of Reader
From page-turners to timeless classics—find your next favorite read.
