158 citations · 182 across the 4 of their papers we have counts for
4 papers · 1 filter
Reaching Data Confidentiality and Model Accountability on the CalTrain
Zhongshu Gu, Hani Jamjoom, Dong Su +5
Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by re…
Confidential Inference via Ternary Model Partitioning
Zhongshu Gu, Heqing Huang, Jialong Zhang +5
Today's cloud vendors are competing to provide various offerings to simplify and accelerate AI service deployment. However, cloud users always have concerns about the confidentiali…
Differentially Private -Means Clustering
Dong Su, Jianneng Cao, Ninghui Li +2
There are two broad approaches for differentially private data analysis. The interactive approach aims at developing customized differentially private algorithms for various data m…
Differentially Private Projected Histograms of Multi-Attribute Data for Classification
Dong Su, Jianneng Cao, Ninghui Li
In this paper, we tackle the problem of constructing a differentially private synopsis for the classification analyses. Several the state-of-the-art methods follow the structure of…