N
Ninghui Li
Researcher at Purdue University
Publications - 266
Citations - 19897
Ninghui Li is an academic researcher from Purdue University. The author has contributed to research in topics: Access control & Differential privacy. The author has an hindex of 70, co-authored 262 publications receiving 17748 citations. Previous affiliations of Ninghui Li include New York University & National Chiao Tung University.
Papers
More filters
Proceedings ArticleDOI
Efficient and accurate strategies for differentially-private sliding window queries
TL;DR: This work proposes two solutions to release differentially private answers for a set of sliding window aggregate queries, each consisting of query sampling and composition, and shows that they are efficient and effective.
Proceedings ArticleDOI
Membership Inference Attacks and Defenses in Classification Models
TL;DR: This work proposes a defense against MI attacks that aims to close the gap by intentionally reduces the training accuracy, by means of a new set regularizer using the Maximum Mean Discrepancy between the softmax output empirical distributions of the training and validation sets.
Book ChapterDOI
On the Security of Delegation in Access Control Systems
Qihua Wang,Ninghui Li,Hong Chen +2 more
TL;DR: A novel source-based enforcement mechanism for workflow authorization systems is designed so as to achieve both security and efficiency and a formal notion of security with respect to delegation is proposed.
Proceedings Article
A Framework for Role-Based Access Control in Group Communication Systems.
Cristina Nita-Rotaru,Ninghui Li +1 more
TL;DR: In this paper, the authors analyze the requirements access control mechanisms must fulfill in the context of group communication and define a framework for supporting fine-grained access control in client-server group communication systems.
Proceedings ArticleDOI
Towards Effective Differential Privacy Communication for Users’ Data Sharing Decision and Comprehension
TL;DR: When shown descriptions that explain the implications instead of the definition/processes of DP or LDP technique, participants demonstrated better comprehension and showed more willingness to share information with LDP than with DP, indicating their understanding of LDP’s stronger privacy guarantee compared with DP.