Y
Yiwen Nie
Researcher at University of Science and Technology of China
Publications - 12
Citations - 284
Yiwen Nie is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Differential privacy & Information privacy. The author has an hindex of 5, co-authored 12 publications receiving 186 citations.
Papers
More filters
Posted Content
Mutual Information Optimally Local Private Discrete Distribution Estimation.
Shaowei Wang,Liusheng Huang,Pengzhan Wang,Yiwen Nie,Hongli Xu,Wei Yang,Xiang-Yang Li,Chunming Qiao +7 more
TL;DR: This work proposes an efficient implementation of the $k$-subset mechanism for discrete distribution estimation, and shows its optimality guarantees over existing approaches.
Journal ArticleDOI
Local Differential Private Data Aggregation for Discrete Distribution Estimation
TL;DR: This work considers distribution estimation over user-contributed data meanwhile providing rigid protection of their data with local $\epsilon$ε-differential privacy ($ε-LDP), which sanitizes each user's data on the client's side (e.g, on the user's mobile device).
Proceedings ArticleDOI
PrivSet: Set-Valued Data Analyses with Locale Differential Privacy
TL;DR: In PrivSet, within the constraints of local e-differential privacy, each user independently responses with a subset of the set-valued data domain with calibrated probabilities, hence the true positive/false positive rate of each item is balanced and the performance of distribution estimation is optimized.
Proceedings ArticleDOI
Local private ordinal data distribution estimation
TL;DR: Under ε-geo-indistinguishable constraints, which capture intrinsic dissimilarity between ordinal categories in the framework of differential privacy, this work provides an efficient and effective locally private mechanism: Subset Exponential Mechanism (SEM) for ordinal data distribution estimation.
Journal ArticleDOI
A Utility-Optimized Framework for Personalized Private Histogram Estimation
TL;DR: This paper designs two independent approaches to minimize the utility loss of histogram estimation and embeds these approaches within a Recycle and Combination Framework and proves that the framework stably achieves the optimal utility by quantifying its error bounds.