Looking for a friendly, accessible way to learn about differential privacy? ๐ง Prefer simple explanations to ugly equations? ๐
Introducing my โจ newly revamped โจ blog post series about differential privacy, now with an intro page & table of contents ๐
https://t.co/bMmRjc1r1w
Hahahaha I'm hearing that posts that mention other social networks by name are de-prioritized in "for you" timelines. What a loser move ๐คฃ
Anyway I'm over there โคต๏ธ
I now have a presence on Bluesky: https://t.co/d35MbIeXzO ๐ฆ
If your main presence is on Bluesky, it'd be fantastic if you could follow https://t.co/jZuvdZDnme, so your posts are also mirrored on Mastodon, and I can follow you from there ๐
Super excited about this โจ new blog post โจ, where I try to offer a super simple & intuitive explanation of the exponential mechanism, a fundamental building block in differential privacy ๐งฑ
Feedback welcome! ๐
https://t.co/SSqnOqDTAi
@ggharibi__@Wikimedia@uscensusbureau Do you know of any publicly available information about this kind of deployment? I've heard some talk in academic circles but I don't know whether anything has been shipped to real products.
Updated my list of real-world deployments of differential privacy! ๐
Changelog:
- Added the @Wikimedia pageview release ๐
- Added two releases by @uscensusbureau ๐บ๐ธ
- Added details on a COVID-19 release from Google ๐
- Various maintenance fixes ๐ ๏ธ
https://t.co/eIEeD2XDwR
@PierreTholoniat @TumultLabs Yes indeed โ I wrote the post long before this paper was on arXiv but it was published afterwards ^^ I'll try to find time to edit it next week to capture these results.
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? ๐ง
This blog post surveys existing results and raises a bunch of overlooked open problems. Feedback welcome! ๐
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 Problemโข ๐ฌ
Feedback super welcome as always! ๐
first arxiv preprint ever๐ซฃ โPublishing Wikipedia usage data with strong privacy guarantees,โ which iโll be presenting at TPDP 2023 in a few weeks
https://t.co/WGBkhD3qCY
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: https://t.co/jd2OmHutvb #pepr23
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 https://t.co/rRMj4lWcGb ๐
@HVitamines Hi, thanks! To analyze the privacy guarantees of this mechanism under ฯ-zCDP, one has to calculate the Rรฉnyi divergence of two Gaussian distributions of different variances. This is the hard part, unless we've missed something obvious?
@PET_Symposium @TumultLabs More info in the paper โ https://t.co/HdjFD4pQtf ๐
And check out the full @PET_Symposium program; there it a ton of fantastic work in there: https://t.co/1wRf1me8Cl โจ
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 ๐
In collaboration with Sam Haney & yours truly ๐
"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"