I am looking to hire a PostDoc in differentially private synthetic data generation MIT-IBM Watson AI Lab. If you are interested in differential privacy and generative modelling, please reach out via email. Recommendations and signal boosting appreciated!

Exciting! A book chapter on composition theorems in #differentialprivacy by Thomas Steinke. Disclaimer: I'm a sucker for everything Thomas writes. arxiv.org/abs/2210.00597

Composition Basics ift.tt/3L4oPfb

Open problem - Better privacy guarantees for larger groups differentialprivacy.org/open-problem-b…

Call for Papers - TPDP 2023 - Submission deadline July 7 differentialprivacy.org/tpdp2023/

#COLT2023 Mark Fulk award for best student paper is shared by two papers

The 2023 Caspar Bowden PET Award winner is: "The 2020 Census Disclosure Avoidance System TopDown Algorithm" #pets23

Covariance-Aware Private Mean Estimation, Efficiently differentialprivacy.org/colt23-bsp/

Beyond Global Sensitivity via Inverse Sensitivity differentialprivacy.org/inverse-sensit…

OpenDP is excited to bring you Library 0.8! Featuring improvements to OpenDP APIs, an early preview of functionality, and quality-of-life improvements. We'll discuss the new release at the OpenDP Community Meeting on September 29! github.com/opendp/opendp

Beyond Local Sensitivity via Down Sensitivity differentialprivacy.org/down-sensitivi…

Open problem(s) - How generic can composition results be? differentialprivacy.org/open-problems-…

NeurIPS 2023 Outstanding Paper: Privacy auditing in just one run differentialprivacy.org/neurips23-op/

Happy new year! As promised, I wrote a blog post on the #NeurIPS2023 Outstanding Paper on privacy auditing, by Thomas Steinke, Milad Nasr, Matthew Jagielski. Post is on Differential Privacy, 5 min read, written for a general ML audience. No knowlege of privacy needed! Link in next tweet👇

Tight RDP & zCDP Bounds from Pure DP differentialprivacy.org/pdp-to-zcdp/

Differentially Private Algorithms that Never Fail differentialprivacy.org/fail-prob/

Privacy Amplification by Subsampling differentialprivacy.org/subsampling/

Limits of Privacy Amplification by Subsampling differentialprivacy.org/subsampling-li…

Open Problem: Selection via Low-Sensitivity Queries differentialprivacy.org/open-problem-s…