activity
20182021
most citedInformation Laundering for Model Privacy

10 citations · 16 across the 7 of their papers we have counts for

collaborators

18 papers

cond-mat.mes-hall2021

Learning Time Series from Scale Information

Yuan Yang, Jie Ding

Sequentially obtained dataset usually exhibits different behavior at different data resolutions/scales. Instead of inferring from data at each scale individually, it is often more…

math.ST20206 cited

On Statistical Efficiency in Learning

Jie Ding, Enmao Diao, Jiawei Zhou +1

A central issue of many statistical learning problems is to select an appropriate model from a set of candidate models. Large models tend to inflate the variance (or overfitting),…

cs.LG2020

ASCII: ASsisted Classification with Ignorance Interchange

Jiaying Zhou, Xun Xian, Na Li +1

The rapid development in data collecting devices and computation platforms produces an emerging number of agents, each equipped with a unique data modality over a particular popula…

math.PR2020

Large Deviation Principle for the Whittaker 2d Growth Model

Jun Gao, Jie Ding

The Whittaker 2d growth model is a triangular continuous Markov diffusion process that appears in many scientific contexts. It has been theoretically intriguing to establish a larg…

cs.CR202010 cited

Information Laundering for Model Privacy

Xinran Wang, Yu Xiang, Jun Gao +1

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model priv…

cs.CR2020

Imitation Privacy

Xun Xian, Xinran Wang, Mingyi Hong +2

In recent years, there have been many cloud-based machine learning services, where well-trained models are provided to users on a pay-per-query scheme through a prediction API. The…