Differential Privacy
From Theory to Practice
Seiten
2016
Morgan & Claypool Publishers (Verlag)
978-1-68173-221-3 (ISBN)
Morgan & Claypool Publishers (Verlag)
978-1-68173-221-3 (ISBN)
- Lieferbar
- Versandkostenfrei
- Auch auf Rechnung
- Artikel merken
Over the last decade, differential privacy (DP) has emerged as the de facto standard privacy notion for research in privacy-preserving data analysis and publishing. The DP notion offers strong privacy guarantee and has been applied to many data analysis tasks.
This Synthesis Lecture is the first of two volumes on differential privacy. This lecture differs from the existing books and surveys on differential privacy in that we take an approach balancing theory and practice. We focus on empirical accuracy performances of algorithms rather than asymptotic accuracy guarantees. At the same time, we try to explain why these algorithms have those empirical accuracy performances. We also take a balanced approach regarding the semantic meanings of differential privacy, explaining both its strong guarantees and its limitations.
We start by inspecting the definition and basic properties of DP, and the main primitives for achieving DP. Then, we give a detailed discussion on the the semantic privacy guarantee provided by DP and the caveats when applying DP. Next, we review the state of the art mechanisms for publishing histograms for low-dimensional datasets, mechanisms for conducting machine learning tasks such as classification, regression, and clustering, and mechanisms for publishing information to answer marginal queries for high-dimensional datasets. Finally, we explain the sparse vector technique, including the many errors that have been made in the literature using it.
The planned Volume 2 will cover usage of DP in other settings, including high-dimensional datasets, graph datasets, local setting, location privacy, and so on. We will also discuss various relaxations of DP.
This Synthesis Lecture is the first of two volumes on differential privacy. This lecture differs from the existing books and surveys on differential privacy in that we take an approach balancing theory and practice. We focus on empirical accuracy performances of algorithms rather than asymptotic accuracy guarantees. At the same time, we try to explain why these algorithms have those empirical accuracy performances. We also take a balanced approach regarding the semantic meanings of differential privacy, explaining both its strong guarantees and its limitations.
We start by inspecting the definition and basic properties of DP, and the main primitives for achieving DP. Then, we give a detailed discussion on the the semantic privacy guarantee provided by DP and the caveats when applying DP. Next, we review the state of the art mechanisms for publishing histograms for low-dimensional datasets, mechanisms for conducting machine learning tasks such as classification, regression, and clustering, and mechanisms for publishing information to answer marginal queries for high-dimensional datasets. Finally, we explain the sparse vector technique, including the many errors that have been made in the literature using it.
The planned Volume 2 will cover usage of DP in other settings, including high-dimensional datasets, graph datasets, local setting, location privacy, and so on. We will also discuss various relaxations of DP.
Ninghui Li, Purdue University. Min Lyu, University of Science and Technology of China. Dong Su, Purdue University. Weining Yang, Purdue University.
Acknowledgments
Introduction
A Primer on ?-Differential Privacy
What Does DP Mean?
Publishing Histograms for Low-dimensional Datasets
Differentially Private Optimization
Publishing Marginals
The Sparse Vector Technique
Bibliography
Authors' Biographies
| Erscheinungsdatum | 19.11.2017 |
|---|---|
| Reihe/Serie | Synthesis Lectures on Information Security, Privacy, and Trust |
| Verlagsort | San Rafael |
| Sprache | englisch |
| Maße | 191 x 235 mm |
| Gewicht | 825 g |
| Themenwelt | Informatik ► Netzwerke ► Sicherheit / Firewall |
| Informatik ► Theorie / Studium ► Kryptologie | |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| ISBN-10 | 1-68173-221-1 / 1681732211 |
| ISBN-13 | 978-1-68173-221-3 / 9781681732213 |
| Zustand | Neuware |
| Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Das Lehrbuch für Konzepte, Prinzipien, Mechanismen, Architekturen und …
Buch | Softcover (2022)
Springer Vieweg (Verlag)
CHF 48,95
eine Cyberstaatsanwältin ermittelt
Buch | Hardcover (2024)
Murmann Publishers (Verlag)
CHF 34,95
