no code implementations • 4 Feb 2022 • Yifeng Zheng, Shangqi Lai, Yi Liu, Xingliang Yuan, Xun Yi, Cong Wang
In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation.
no code implementations • 14 Nov 2019 • Shangqi Lai, Xingliang Yuan, Amin Sakzad, Mahsa Salehi, Joseph K. Liu, Dongxi Liu
It realises several cryptographic modules via efficient and interchangeable protocols to support the above cryptographic operations and composes them in the overall protocol to enable outlier detection over encrypted datasets.