Looking for a friendly, accessible way to learn about differential privacy? 🧐 Prefer simple explanations to ugly equations? 😇
Introducing my ✨ newly revamped ✨ blog post series about differential privacy, now with an intro page & table of contents 🌈
desfontain.es/privacy/friend…
Hahahaha I'm hearing that posts that mention other social networks by name are de-prioritized in "for you" timelines. What a loser move 🤣
Anyway I'm over there ⤵️
I now have a presence on Bluesky: bsky.app/profile/desfontain.… 🦋
If your main presence is on Bluesky, it'd be fantastic if you could follow bsky.app/profile/ap.brid.gy, so your posts are also mirrored on Mastodon, and I can follow you from there 💖
Super excited about this ✨ new blog post ✨, where I try to offer a super simple & intuitive explanation of the exponential mechanism, a fundamental building block in differential privacy 🧱
Feedback welcome! 💝
desfontain.es/privacy/choosi…
Updated my list of real-world deployments of differential privacy! 🚀
Changelog:
- Added the @Wikimedia pageview release 🌐
- Added two releases by @uscensusbureau 🇺🇸
- Added details on a COVID-19 release from Google 💉
- Various maintenance fixes 🛠️
desfontain.es/privacy/real-w…
New, by me: what do we know about differential privacy composition theorems? What's missing, and would be useful to folks who are building practical DP software? 🔧
This blog post surveys existing results and raises a bunch of overlooked open problems. Feedback welcome! 💖
New blog post co-written by yours truly! In which we look at data clean rooms, what they do, what they often don't do, and why that can be a Problem™ 😬
Feedback super welcome as always! 🌈
first arxiv preprint ever🫣 “Publishing Wikipedia usage data with strong privacy guarantees,” which i’ll be presenting at TPDP 2023 in a few weeks
arxiv.org/abs/2308.16298
Hear it at 2023 USENIX Conference on Privacy Engineering Practice and Respect: *Privacy-Preserving Analytics on the Ground* presented by Ryan Steed (Carnegie Mellon University). View the program and register now: bit.ly/pepr23prog#pepr23
If you're at @PET_Symposium next week, don't miss Marika Swanberg's talk about her research at @TumultLabs last summer: a novel DP mechanism for partition selection which, in contrast to prior work, scales horizontally 📈
In collaboration with Sam Haney & yours truly 😊
"When we want to protect individuals whose data is distributed across multiple rows, protecting individual rows is not enough." @TumultLabs introduces privacy IDs, .. "privacy identifiers enable the protection of individuals across large datasets, no matter how often they appear"
And now for something different: during a customer engagement, we stumbled upon a natural, but surprisingly tricky open problem in differential privacy. We couldn't figure it out, so we posted a simplified version of it as an open problem on DifferentialPrivacy.org 👀
Woo-hoo, this is a huge step for Tumult Analytics! 🤩
Privacy IDs are a super important feature, and making it work with all our other advanced features was no small feat 😊
Check out the blog post we wrote to explain what problem it solves, and how it works in practice ✨
I'll give a talk there! About floating-point vulnerabilities in differential privacy software. Mark the ticket sales on your calendar, from what I hear, tickets run out fast!
excuse me while I earnest-post about my work for a sec!! along with @TumultLabs I helped @Wikimedia release ~250 million private pageview stats, covering ~1 *trillion* pageviews from wikipedia and other projects from 8 years of browsing activity
Did you know that we release data about pageviews of every Wikimedia project hourly?
But we were asked to go further.
In partnership with @TumultLabs, we released today almost 8 years of pageview data divided by country, project, and page. Take a look ⬇️
w.wiki/6rh6
It was such a privilege to work with @Wikimedia folks on this data release 💙
They care a *ton* about the privacy of Wikipedia users, and also wanted to uphold the nonprofit's commitment to transparency and open data 🔓
A perfect job for differential privacy! ✨
Did you know that we release data about pageviews of every Wikimedia project hourly?
But we were asked to go further.
In partnership with @TumultLabs, we released today almost 8 years of pageview data divided by country, project, and page. Take a look ⬇️
w.wiki/6rh6