Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Vadhan, Salil P."'
Given a sequence of samples $x_1, \dots , x_k$ promised to be drawn from one of two distributions $X_0, X_1$, a well-studied problem in statistics is to decide $\textit{which}$ distribution the samples are from. Information theoretically, the maximum
Externí odkaz:
http://arxiv.org/abs/2412.03562
A series of recent works by Lyu, Wang, Vadhan, and Zhang (TCC `21, NeurIPS `22, STOC `23) showed that composition theorems for non-interactive differentially private mechanisms extend to the concurrent composition of interactive differentially privat
Externí odkaz:
http://arxiv.org/abs/2411.03299
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 contex
Externí odkaz:
http://arxiv.org/abs/2410.09721
Autor:
Ratliff, Zachary, Vadhan, Salil
The standard definition of differential privacy (DP) ensures that a mechanism's output distribution on adjacent datasets is indistinguishable. However, real-world implementations of DP can, and often do, reveal information through their runtime distr
Externí odkaz:
http://arxiv.org/abs/2409.05623
Many programming frameworks have been introduced to support the development of differentially private software applications. In this chapter, we survey some of the conceptual ideas underlying these frameworks in a way that we hope will be helpful for
Externí odkaz:
http://arxiv.org/abs/2403.11088
Publikováno v:
Transactions on Machine Learning Research (2024)
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this work, we propo
Externí odkaz:
http://arxiv.org/abs/2403.04451
We present connections between the recent literature on multigroup fairness for prediction algorithms and classical results in computational complexity. Multiaccurate predictors are correct in expectation on each member of an arbitrary collection of
Externí odkaz:
http://arxiv.org/abs/2312.17223
Since their inception Generative Adversarial Networks (GANs) have been popular generative models across images, audio, video, and tabular data. In this paper we study whether given access to a trained GAN, as well as fresh samples from the underlying
Externí odkaz:
http://arxiv.org/abs/2310.12063
Autor:
Haney, Samuel, Shoemate, Michael, Tian, Grace, Vadhan, Salil, Vyrros, Andrew, Xu, Vicki, Zhang, Wanrong
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 prov
Externí odkaz:
http://arxiv.org/abs/2309.05901
This is an overview of some of the works of Avi Wigderson, 2021 Abel prize laureate. Wigderson's contributions span many fields of computer science and mathematics. In this survey we focus on four subfields: cryptography, pseudorandomness, computatio
Externí odkaz:
http://arxiv.org/abs/2307.09524