Michael Shoemate

Michael Shoemate

Auto-generated profile, based on publicly available information

Michael Shoemate

Harvard University, Cambridge, Massachusetts, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 November 2023
Verified
Conference Paper
Open access
SHSamuel Haney
Samuel Haney
MSMichael Shoemate
Michael Shoemate
GTGrace Tian
Grace Tian
SVSalil Vadhan
Salil Vadhan
AVAndrew Vyrros
Andrew Vyrros
WZWanrong Zhang
Wanrong Zhang
In this paper, we study the concurrent composition of interactive mechanisms with adaptively chosen privacy-loss parameters. In this setting, the adversary can interleave queries to existing interactive mechanisms, as well as create new ones. We prove that every valid privacy filter and odometer for noninteractive mechanisms extends to the concurrent composition of interactive mechanisms if privacy loss is measured using (ε, δ)-DP, ƒ-DP, or Rényi DP of fixed order. Our results offer strong theoretical foundations for enabling full adaptivity in composing differentially private interactive mechanisms, showing that concurrency does not affect the privacy guarantees. We also provide an implementation for users to deploy in practice.

7 November 2024 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
PSPatrick Song
Patrick Song
JSJayshree Sarathy
Jayshree Sarathy
MSMichael Shoemate
Michael Shoemate
SVSalil Vadhan
Salil Vadhan
Differential privacy (DP) is a promising framework for privacy-preserving data science, but recent studies have exposed challenges in bringing this theoretical framework for privacy into practice. These tensions are particularly salient in the context of open-source software libraries for DP data analysis, which are emerging tools to help data stewards and analysts build privacy-preserving data pipelines for their applications. While there has been significant investment into such libraries, we need further inquiry into the role of these libraries in promoting understanding of and trust in DP, and in turn, the ways in which design of these open-source libraries can shed light on the challenges of creating trustworthy data infrastructures in practice. In this study, we use qualitative methods and mental models approaches to analyze the differences between conceptual models used to design open-source DP libraries and mental models of DP held by users. Through a two-stage study design involving formative interviews with 5 developers of open-source DP libraries and user studies with 17 data analysts, we find that DP libraries often struggle to bridge the gaps between developer and user mental models. In particular, we highlight the tension DP libraries face in maintaining rigorous DP implementations and facilitating user interaction. We conclude by offering practical recommendations for further development of DP libraries.

22 April 2019 in Journal of Open Source Software
Verified
Journal Article
Open access
PDF file
HKHyoungAh Kim
HyoungAh Kim
VDVito D’oRazio
Vito D’oRazio
PBPatrick Brandt
Patrick Brandt
JLJared Looper
Jared Looper
SSSayeed Salam
Sayeed Salam
MSMichael Shoemate
Michael Shoemate