Sign inSign in
ConceptAI & ML

Differential privacy

A mathematical definition of privacy ensuring that an algorithm's output does not reveal whether any single individual's data was included in the dataset.
as Gavin Brown defines itCaltechThe wording closest to all 9 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Probability distribution6Randomized algorithm4Datasets2Probability2Auxiliary information1Data privacy1Indistinguishability1Randomized mechanisms1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

9

Each in their own terms, from the easiest level.

  • Michael I. Jordan

    UC Berkeley · Graduate

    A privacy method that adds noise to data while preserving useful aggregate patterns.
    • 43:10A Collectivist, Economic Perspective on AI Systems
  • Cynthia Dwork

    UC Berkeley · Graduate

    A definition stating that the outcome of any statistical analysis is essentially equally likely whether any individual joins or refrains from joining the dataset.
    • 8:42Differential Privacy: Fundamentals to Forefront I
  • Charlie Hou

    Google Research & TechTalks · Graduate

    A mathematical framework ensuring that the output of an algorithm does not change significantly if any single individual's data is added to or removed from the training dataset.
    • 2:34POPRi: Private Federated Learning using Preference-Optimized Synthetic Data
  • Adam Dziedzic

    Caltech · Graduate

    Produces roughly same or indistinguishable outputs on any pair of prompt datasets that differ only by a single data point.
    • 10:10Private Adaptations of Large Language Models
  • Connor Wagaman

    Google Research & TechTalks · Research

    A definition imposing a restriction on algorithms where running that algorithm on data sets that differ by one individual results in outputs that are hard to tell apart.
    • 2:32Local Node Differential Privacy
  • Andy Dong

    Google Research & TechTalks · Research

    A mathematical framework for measuring the privacy guarantees of algorithms, defined here via hockey-stick divergence over adjacent datasets.
    • 5:04Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
  • Kai Chen

    Google Research & TechTalks · Research

    An algorithm M satisfies epsilon-delta DP if neighboring datasets differing in one record produce very close output distributions controlled by epsilon and delta.
    • 1:09Differentially Private Table-Image Multimodal Data Generation
  • Katrina Ligett

    UC Berkeley · Research

    A mathematical framework for measuring the privacy loss of a randomized algorithm when individual data points are changed.
    • 23:40Foundations, Privacy & Generalization Challenges in Modern Machine Learning

Lectures that assume it

3

Connections

20

The lectures that define it or assume it, and the concepts next to it.

9 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.