A Course on Differential Privacy (差分隐私)
CS 860: Algorithms for Private Data Analysis
University of Waterloo, Fall 2020
滑铁卢大学计算机系研究生第一年课程：隐私数据分析
课程网站及笔记: http://www.gautamkamath.com/CS860-fa2020.html
- 字幕制作者（中文（简体））：nature-art
- 字幕制作者（English(US)）：刘巍然-学酥
滑铁卢大学计算机教授：机器学习，统计
视频选集
（1/38）
Lecture 1A: Some Attempts at Data Privacy - NYC Taxis and Netflix
27:22
Lecture 1B: Some Attempts at Data Privacy - Neural Networks, Medical Studies
30:00
Lecture 2A: Reconstruction and a Census
21:31
Lecture 2B: Reconstruction by Dinur-Nissim
46:12
Lecture 2C: Reconstruction via Dinur-Nissim on Diffix
15:44
Lecture 3A: Randomized Response
22:28
Lecture 3B: The Definition of Differential Privacy
57:34
Lecture 4A: The Laplace Mechanism
52:41
Lecture 4B: Properties of Differential Privacy
16:34
Lecture 5A: Approximate Differential Privacy
43:52
Lecture 5B: The Gaussian Mechanism and Properties of Approximate DP
49:25
Lecture 6A: Advanced Composition Proof Start
28:39
Lecture 6B: Advanced Composition Proof End
33:58
Lecture 7A: The Exponential Mechanism
36:59
Lecture 7B: Applications of the Exponential Mechanism
39:29
Lecture 8A: Private Multiplicative Weights - Linear Queries
19:42
Lecture 8B: Private Multiplicative Weights - Non-Private Multiplicative Weights
53:42
Lecture 8C: Private Multiplicative Weights - Multiplicative Weights for Queries
47:07
Lecture 9A: Sparse Vector - Above Threshold
43:12
Lecture 9B: Sparse Vector - SparseVector, and Online PMW
26:42
Lecture 10A: Beyond Global Sensitivity
43:31
Lecture 10B: Also Beyond Global Sensitivity
34:23
Lecture 11: Packing Lower Bounds
54:57
Lecture 12: What is Privacy?
31:13
Lecture 13A: Differentially Private Machine Learning - A Quick Primer
43:54
Lecture 13B: Differentially Private ML - Output & Objective Perturbation
24:19
Lecture 13C: Differentially Private Machine Learning - Gradient Perturbation
37:49
Lecture 14A: Modern Private ML - Some Background on Neural Networks
21:25
Lecture 14B: Modern Private ML - DP Stochastic Gradient Descent
01:00:20
Lecture 14C: Modern Private ML - PATE
30:09
Lecture 15A: Private Mean Estimation - Introduction
52:57
Lecture 15B: Private Mean Estimation - Near-Optimal Univariate Gaussians
40:12
Lecture 15C: Private Mean Estimation - Beyond Univariate Gaussians
37:29
Lecture 16A: Adaptive Data Analysis - Intro, Setup, and Results
41:13
Lecture 16B: Adaptive Data Analysis - Proofs
19:49
Lecture 17A: DP Deployments 1, Local DP
51:27
Lecture 17B: DP Deployments 1, Local DP
42:06
Lecture 18: DP Deployments 2
01:24:46
顶部