Search Results for author:
Found 12 papers, 4 papers with code
Optimal Differential Privacy Composition for Exponential Mechanisms
We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP.
Error-Tolerant E-Discovery Protocols
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.
Classification Protocols with Minimal Disclosure
We consider multi-party protocols for classification that are motivated by applications such as e-discovery in court proceedings.
Privacy Amplification via Iteration for Shuffled and Online PNSGD
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.
Optimal Accounting of Differential Privacy via Characteristic Function
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.
Rejoinder: Gaussian Differential Privacy
In this rejoinder, we aim to address two broad issues that cover most comments made in the discussion.
A Central Limit Theorem for Differentially Private Query Answering
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.
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
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.
Deep Learning with Gaussian Differential Privacy
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.
Equilibrium Characterization for Data Acquisition Games
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.
Gaussian Differential Privacy
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.
Strategic Classification from Revealed Preferences
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.
