J
Junzhe Xia
Researcher at Hong Kong University of Science and Technology
Publications - 3
Citations - 256
Junzhe Xia is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Information privacy & Collaborative learning. The author has an hindex of 2, co-authored 3 publications receiving 72 citations.
Papers
More filters
Proceedings Article
BatchCrypt: Efficient homomorphic encryption for cross-silo federated learning
TL;DR: BatchCrypt is presented, a system solution for cross-silo FL that substantially reduces the encryption and communication overhead caused by HE, and develops new quantization and encoding schemes along with a novel gradient clipping technique.
Proceedings ArticleDOI
Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning
Chengliang Zhang,Junzhe Xia,Baichen Yang,Huancheng Puyang,Wei Wang,Ruichuan Chen,Istemi Ekin Akkus,Paarijaat Aditya,Feng Yan +8 more
TL;DR: Citadel as mentioned in this paper is a scalable collaborative ML system that protects both data and model privacy in untrusted infrastructures equipped with Intel SGX, which performs distributed training across multiple training enclaves running on behalf of data owners and an aggregator enclave on the behalf of the model owner.
Posted Content
Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX
Chengliang Zhang,Junzhe Xia,Baichen Yang,Huancheng Puyang,Wei Wang,Ruichuan Chen,Istemi Ekin Akkus,Paarijaat Aditya,Feng Yan +8 more
TL;DR: Citadel as discussed by the authors is a scalable collaborative ML system that protects the privacy of both data owner and model owner in untrusted infrastructures with the help of Intel SGX.