Comments (6)
The two above are what I would consider the canonical level 0 and level 1 introductions.
- On the complexity of DP: https://privacytools.seas.harvard.edu/files/privacytools/files/complexityprivacy_1.pdf
- what I would consider a level 2 introduction to a bunch of concepts in the field
- Laplace mechanism: https://people.csail.mit.edu/asmith/PS/sensitivity-tcc-final.pdf
- Snapping mechanism and how floating-point numbers and the laplace mechanism leak:
https://www.microsoft.com/en-us/research/wp-content/uploads/2012/10/lsbs.pdf - Exponential mechanism: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/mdviadp.pdf
- Geometric mechanism: https://arxiv.org/pdf/1709.05396.pdf (not the first geometric mech paper, but more approachable)
- More on sample/aggregate, and quantiles: https://cs-people.bu.edu/ads22//pubs/2011/stoc194-smith.pdf
- Gradient descent: https://arxiv.org/pdf/1607.00133.pdf
- Renyi DP: https://arxiv.org/pdf/1702.07476.pdf
- zCDP: https://arxiv.org/pdf/1605.02065.pdf
from docs.smartnoise.org.
- Nice intro level presentation: https://www2.census.gov/cac/nac/meetings/2019-05/garfinkel-privacy-confidentiality-protection.pdf
- More resources: https://simson.net/page/Differential_privacy
MS Broadband paper: https://arxiv.org/pdf/2103.14035.pdf
from docs.smartnoise.org.
From Salil:
https://privacytools.seas.harvard.edu/courses-educational-materials
from docs.smartnoise.org.
Can we already put the "Resources" page up on our doc site and/or our website?
from docs.smartnoise.org.
The doc site is a bit in flux (we're working on moving the source to the main repo at opendp/opendp#170 ) but I don't see why these resources couldn't go on the website, like you said.
While I'm commenting, Here are a few more resources from Salil and Mike from Slack:
- Two more resources: this chapter is more up-to-date and a bit more aimed at practitioners than the primer: https://admindatahandbook.mit.edu/book/latest/diffpriv.html
- And differentialprivacy.org has more resources too
- https://uvm-plaid.github.io/programming-dp/notebooks/cover.html
from docs.smartnoise.org.
Closing in favor of opendp/opendp#272
Some more responses via Slack:
We have a list of resources here (click on "Learning about DP -> Books and Surveys"): https://privacytools.seas.harvard.edu/courses-educational-materials
Two more resources: this chapter is more up-to-date and a bit more aimed at practitioners than the primer: https://admindatahandbook.mit.edu/book/latest/diffpriv.html
And https://differentialprivacy.org has more resources too
from docs.smartnoise.org.
Related Issues (20)
- "hidden features" documentation
- documentation touch-up
- unable to preview changes
- ability to preview HTML from pull requests online
- SmartNoise Docs, add python version compatibility HOT 1
- Start "Discussions" on opendp/opendp
- Broken link HOT 1
- Switch Slack orgs
- Cannot built docs: AttributeError: module 'opendp.smartnoise.synthesizers' has no attribute 'QUAILSynthesizer' HOT 6
- Windows build needs special compilation flag
- builds from GitHub Actions don't fail on warnings HOT 1
- link to Twitter account HOT 1
- Contact page, GitHub Discussions vs Google Group
- notebook testing
- Does the pull request build?
- emphasize need to use Python 3.8 HOT 1
- Add Announcements section to GH Discussions
- Convert this repo to SmartNoise docs only HOT 2
- Add deprecation warning to docs
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from docs.smartnoise.org.