Tutorial: Differential Privacy and Learning: The Tools, The Results, and The Frontier

preview_player
Показать описание
When is working with private data safe, and when is it risky? Are the risks inherent to the computation? Widespread availability of detailed personal data makes understanding privacy necessaryΓÇöan exciting yet daunting challenge. Differential privacy provides a framework for understanding the tradeoff between the loss of privacy for those whose data are input to a computation and the accuracy of that computationΓÇÖs output. This tutorial will not assume familiarity with differential privacy. We will cover the necessary definitions, help build intuition, and introduce the basic differential privacy toolkit. We will then highlight some connections to learning in the existing differential privacy literature, and challenges and open problems for differentially private learning tasks.
  1. Microsoft Research
  2. microsoft research
Рекомендации по теме
Differential Privacy - 0:06:59

Differential Privacy - Simply Explained

Tutorial: Differential Privacy 1:55:51

Tutorial: Differential Privacy and Learning: The Tools, The Results, and The Frontier

Differential Privacy + 0:07:26

Differential Privacy + Federated Learning Explained (+ Tutorial) | #AI101

EACL 2023 Tutorial 0:40:10

EACL 2023 Tutorial on Privacy-preserving NLP: Formal guarantees with differential privacy

Differential Privacy, the 0:59:30

Differential Privacy, the Tutorial 1/3

Privacy Preserving AI 1:13:51

Privacy Preserving AI (Andrew Trask) | MIT Deep Learning Series

OM PriCon2020 Tutorial: 0:47:07

OM PriCon2020 Tutorial: Differential Privacy Using PyDP - Chinmay Shah

Federated Learning And 0:04:59

Federated Learning And Differential Privacy

OM PriCon 2020 0:53:08

OM PriCon 2020 Tutorial: Differentially Private Model Training with Opacus - Davide Testuggine

Building Differentially private 0:25:53

Building Differentially private Machine Learning Models Using TensorFlow Privacy | Chang Liu

SaTML 2023 - 0:59:30

SaTML 2023 - Gautam Kamath - An Introduction to Differential Privacy

Tutorial: Privacy at 1:28:08

Tutorial: Privacy at Scale: Local Differential Privacy in Practice

Differential Privacy in 0:05:37

Differential Privacy in Federated Learning - Owndata

A short tutorial 1:48:40

A short tutorial on differential privacy: Dr Borja Balle, Amazon Research

PyTorch Opacus Tutorial 0:51:53

PyTorch Opacus Tutorial | Deep Learning with Differential Privacy | Cologne AI & ML

Differential Privacy, the 0:56:54

Differential Privacy, the Tutorial 2/3

Differential Privacy in 0:13:41

Differential Privacy in Federated Learning

NASIT 2019 Tutorial 3:13:36

NASIT 2019 Tutorial - Adam Smith - Differential Privacy

Differential Privacy For 0:23:56

Differential Privacy For Machine Learning In Action (Sensitive Data)

CCS 2016 - 0:29:10

CCS 2016 - Deep Learning with Differential Privacy

Differential Privacy in 0:21:01

Differential Privacy in Machine Learning with TensorFlow Privacy

Differential Privacy, the 0:51:23

Differential Privacy, the Tutorial 3/3

Differential Privacy in 0:05:37

Differential Privacy in Machine Learning with TensorFlow Privacy | #qwiklabs | #coursera @quick_lab

Differential Privacy on 0:11:26

Differential Privacy on PyTorch | PyTorch Developer Day 2020

Комментарии
Автор

Thank you for making this video available. I have learned a lot from it.

GamalElkomy
Автор

what do you mean by "unaffected by auxiliary information and independent of adversary's computational power"?

macknightxu
Автор

... is multiplicably very close to ....

macknightxu
Автор

It’s stupid and archaic for mathematicians to name things arbitrarily. epsilon? You would get fired for such poor code/algorithm. Programmers learned this 40 years ago.

lukeno