Theory of cryptography | Differential privacy
Differential privacy (DP) is a system for publicly sharing information about a dataset by describing the patterns of groups within the dataset while withholding information about individuals in the dataset.The idea behind differential privacy is that if the effect of making an arbitrary single substitution in the database is small enough, the query result cannot be used to infer much about any single individual, and therefore provides privacy. Another way to describe differential privacy is as a constraint on the algorithms used to publish aggregate information about a statistical database which limits the disclosure of private information of records whose information is in the database. For example, differentially private algorithms are used by some government agencies to publish demographic information or other statistical aggregates while ensuring confidentiality of survey responses, and by companies to collect information about user behavior while controlling what is visible even to internal analysts. Roughly, an algorithm is differentially private if an observer seeing its output cannot tell if a particular individual's information was used in the computation.Differential privacy is often discussed in the context of identifying individuals whose information may be in a database. Although it does not directly refer to identification and reidentification attacks, differentially private algorithms probably resist such attacks. Differential privacy was developed by cryptographers and thus is often associated with cryptography, and draws much of its language from cryptography. (Wikipedia).
"I need a better description": An Investigation Into User Expectations For Differential Privacy
A Google TechTalk, presented by Rachel Cummings, 2021/03/12 ABSTRACT: Differential Privacy for ML Series. Despite recent widespread deployment of differential privacy, relatively little is known about what users think of differential privacy. In this work, we seek to explore users' privac
From playlist Differential Privacy for ML
The Definition of Differential Privacy - Cynthia Dwork
Differential Privacy Symposium: Four Facets of Differential Privacy Saturday, November 12, 2016 https://www.ias.edu/differential-privacy More videos on http://video.ias.edu
From playlist Differential Privacy Symposium - November 12, 2016
Composition: The Key to Differential Privacy is Success - Guy Rothblum
Differential Privacy Symposium: Four Facets of Differential Privacy Saturday, November 12, 2016 https://www.ias.edu/differential-privacy More videos on http://video.ias.edu
From playlist Differential Privacy Symposium - November 12, 2016
Nexus Trimester - Adam Smith (Penn State) - 2/3
Differential Privacy, the Tutorial - 2/3 Abstract: The tutorial will introduce differential privacy, a widely used definition of privacy for statistical databases. We will begin with the motivation for rigorous definitions of privacy in statistical databases, covering several examples of
From playlist Nexus Trimester - 2016 - Secrecy and Privacy Theme
Differentially Private Algorithms: Some Primitives and Paradigms - Kunal Talwar
Differential Privacy Symposium: Four Facets of Differential Privacy Saturday, November 12, 2016 https://www.ias.edu/differential-privacy More videos on http://video.ias.edu
From playlist Differential Privacy Symposium - November 12, 2016
Differential Privacy in...Considerations - Helen Nissenbaum
Differential Privacy Symposium: Four Facets of Differential Privacy Saturday, November 12, 2016 https://www.ias.edu/differential-privacy More videos on http://video.ias.edu
From playlist Differential Privacy Symposium - November 12, 2016
Protecting Privacy with MATH (Collab with the Census)
This video was made in collaboration with the US Census Bureau and fact-checked by Census Bureau scientists. Any opinions and errors are my own. For more information, visit https://census.gov/about/policies/privacy/statistical_safeguards.html or search "differential privacy" at http://cens
From playlist MinutePhysics
Nexus Trimester - Adam Smith (Penn State) - 1/3
Differential Privacy, the Tutorial - 1/3 Adam Smith (Penn State) March 30, 2016 Abstract: The tutorial will introduce differential privacy, a widely used definition of privacy for statistical databases. We will begin with the motivation for rigorous definitions of privacy in statistical
From playlist Nexus Trimester - 2016 - Secrecy and Privacy Theme
Nexus Trimester - Adam Smith (Penn State) - 3/3
Differential Privacy, the Tutorial - 3/3 Adam Smith (Penn State) March 30, 2016 Abstract: The tutorial will introduce differential privacy, a widely used definition of privacy for statistical databases. We will begin with the motivation for rigorous definitions of privacy in statistical
From playlist Nexus Trimester - 2016 - Secrecy and Privacy Theme
A short tutorial on differential privacy: Dr Borja Balle, Amazon Research
Differential privacy is a robust mathematical framework for designing privacy-preserving computations on sensitive data. In this tutorial we will cover the key definitions and intuitions behind differential privacy and introduce the core building blocks used by most differentially private
From playlist Turing Seminars
Privacy as Stability, for Generalization - Katrina Legitt
Computer Science/Discrete Mathematics Seminar I Topic: Privacy as Stability, for Generalization Speaker: Katrina Legitt Affiliation: Hebrew University Date: April 12, 2021 For more video please visit http://video.ias.edu
From playlist Mathematics
Experimenting w/ Local & Central Differential Privacy for Both Robustness & Privacy in Fed.Learning
A Google TechTalk, presented by Emiliano De Cristofaro, University College London, at the 2021 Google Federated Learning and Analytics Workshop, Nov. 8-10, 2021. For more information about the workshop: https://events.withgoogle.com/2021-workshop-on-federated-learning-and-analytics/#conte
From playlist 2021 Google Workshop on Federated Learning and Analytics
Turing Lecture: Dr Cynthia Dwork, Privacy-Preserving Data Analysis
Doctor Cynthia Dwork: Privacy-Preserving Data Analysis Privacy-preserving data analysis has a long history, spanning at least five decades and numerous disciplines. Despite this extensive history, it is only in the last decade that an understanding has formed of the risk that the accumula
From playlist Turing Lectures
Learning discrete distributions: User vs item-level privacy
A Google TechTalk, 2020/7/30, presented by Ananda Theertha Suresh, Google ABSTRACT:
From playlist 2020 Google Workshop on Federated Learning and Analytics
Nexus trimester - Sewoong Oh (University of Illinois)
Privacy Region and its Applications Sewoong Oh (University of Illinois) March 31, 2016 Abstract: Interactive querying of a database degrades the privacy level. In this paper we answer the fundamental question of characterizing the level of differential privacy degradation as a function of
From playlist Nexus Trimester - 2016 - Secrecy and Privacy Theme
Profile-based Privacy for Locally Private Computations
A Google TechTalk, 2020/7/30, presented by Kamalika Chaudhuri, UCSD ABSTRACT: Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant commonly used for federated learning is local differential privacy, where the data holder is the trusted
From playlist 2020 Google Workshop on Federated Learning and Analytics