1 code implementation • 7 Mar 2024 • Nico Manzonelli, Wanrong Zhang, Salil Vadhan
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data.
1 code implementation • 13 Jun 2023 • Alyssa Huang, Peihan Liu, Ryumei Nakada, Linjun Zhang, Wanrong Zhang
The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks.
1 code implementation • 10 Mar 2023 • Wanrong Zhang, Ruqi Zhang
In this paper, we study Metropolis-Hastings (MH), one of the most fundamental MCMC methods, for large-scale Bayesian inference under differential privacy.
no code implementations • 10 Apr 2022 • Wanrong Zhang, Yajun Mei, Rachel Cummings
We also empirically validate our theoretical results on several synthetic databases, showing that our algorithms also perform well in practice.
no code implementations • 24 Sep 2020 • Wanrong Zhang, Yajun Mei
In many real-world problems of real-time monitoring high-dimensional streaming data, one wants to detect an undesired event or change quickly once it occurs, but under the sampling control constraint in the sense that one might be able to only observe or use selected components data for decision-making per time step in the resource-constrained environments.
no code implementations • 8 Sep 2020 • Wanrong Zhang, Olga Ohrimenko, Rachel Cummings
We propose definitions to capture \emph{attribute privacy} in two relevant cases where global attributes may need to be protected: (1) properties of a specific dataset and (2) parameters of the underlying distribution from which dataset is sampled.
1 code implementation • 12 Jun 2020 • Wanrong Zhang, Shruti Tople, Olga Ohrimenko
Using multiple machine learning models, we show that leakage occurs even if the sensitive attribute is not included in the training data and has a low correlation with other attributes or the target variable.
1 code implementation • 27 Feb 2020 • Wanrong Zhang, Gautam Kamath, Rachel Cummings
In this work, we study False Discovery Rate (FDR) control in multiple hypothesis testing under the constraint of differential privacy for the sample.
no code implementations • ICML 2020 • Rachel Cummings, Sara Krehbiel, Yuliia Lut, Wanrong Zhang
Much of the prior work on change-point detection---including the only private algorithms for this problem---requires complete knowledge of the pre-change and post-change distributions.
no code implementations • NeurIPS 2018 • Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, Wanrong Zhang
The change-point detection problem seeks to identify distributional changes at an unknown change-point k* in a stream of data.