no code implementations • ICML 2020 • Jinshuo Dong, David Durfee, Ryan Rogers
We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP.
no code implementations • 31 Jan 2024 • Jinshuo Dong, Jason D. Hartline, Liren Shan, Aravindan Vijayaraghavan
Our goal is to find a protocol that verifies that the responding party sends almost all responsive documents while minimizing the disclosure of non-responsive documents.
no code implementations • 6 Sep 2022 • Jinshuo Dong, Jason Hartline, Aravindan Vijayaraghavan
We consider multi-party protocols for classification that are motivated by applications such as e-discovery in court proceedings.
no code implementations • 20 Jun 2021 • Matteo Sordello, Zhiqi Bu, Jinshuo Dong
We then analyze the online setting and provide a faster decaying scheme for the magnitude of the injected noise that also guarantees the convergence of privacy loss.
1 code implementation • 16 Jun 2021 • Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang
Characterizing the privacy degradation over compositions, i. e., privacy accounting, is a fundamental topic in differential privacy (DP) with many applications to differentially private machine learning and federated learning.
no code implementations • 5 Apr 2021 • Jinshuo Dong, Aaron Roth, Weijie J. Su
In this rejoinder, we aim to address two broad issues that cover most comments made in the discussion.
no code implementations • NeurIPS 2021 • Jinshuo Dong, Weijie J. Su, Linjun Zhang
The central question, therefore, is to understand which noise distribution optimizes the privacy-accuracy trade-off, especially when the dimension of the answer vector is high.
1 code implementation • ICML 2020 • Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
To address this question, we introduce a family of analytical and sharp privacy bounds under composition using the Edgeworth expansion in the framework of the recently proposed f-differential privacy.
3 code implementations • 26 Nov 2019 • Zhiqi Bu, Jinshuo Dong, Qi Long, Weijie J. Su
Leveraging the appealing properties of $f$-differential privacy in handling composition and subsampling, this paper derives analytically tractable expressions for the privacy guarantees of both stochastic gradient descent and Adam used in training deep neural networks, without the need of developing sophisticated techniques as [3] did.
no code implementations • 22 May 2019 • Jinshuo Dong, Hadi Elzayn, Shahin Jabbari, Michael Kearns, Zachary Schutzman
We demonstrate a reduction from this potentially complicated action space to a one-shot, two-action game in which each firm only decides whether or not to buy the data.
3 code implementations • 7 May 2019 • Jinshuo Dong, Aaron Roth, Weijie J. Su
More precisely, the privacy guarantees of \emph{any} hypothesis testing based definition of privacy (including original DP) converges to GDP in the limit under composition.
no code implementations • 22 Oct 2017 • Jinshuo Dong, Aaron Roth, Zachary Schutzman, Bo Waggoner, Zhiwei Steven Wu
We study an online linear classification problem, in which the data is generated by strategic agents who manipulate their features in an effort to change the classification outcome.