no code implementations • 8 Dec 2022 • Ergute Bao, Yizheng Zhu, Xiaokui Xiao, Yin Yang, Beng Chin Ooi, Benjamin Hong Meng Tan, Khin Mi Mi Aung
Deep neural networks have strong capabilities of memorizing the underlying training data, which can be a serious privacy concern.
no code implementations • 29 Sep 2021 • Ergute Bao, Yizheng Zhu, Xiaokui Xiao, Yin Yang, Beng Chin Ooi, Benjamin Hong Meng Tan, Khin Mi Mi Aung
We point out a major challenge in this problem setting: that common mechanisms for enforcing DP in deep learning, which require injecting \textit{real-valued noise}, are fundamentally incompatible with MPC, which exchanges \textit{finite-field integers} among the participants.
no code implementations • 6 Feb 2021 • Yuxiao Lu, Jie Lin, Chao Jin, Zhe Wang, Min Wu, Khin Mi Mi Aung, XiaoLi Li
Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures.
no code implementations • 19 Aug 2019 • Ahmad Al Badawi, Luong Hoang, Chan Fook Mun, Kim Laine, Khin Mi Mi Aung
In the second part, we show how to train a model using fully encrypted data to generate an encrypted model.
no code implementations • 2 Nov 2018 • Ahmad Al Badawi, Jin Chao, Jie Lin, Chan Fook Mun, Jun Jie Sim, Benjamin Hong Meng Tan, Xiao Nan, Khin Mi Mi Aung, Vijay Ramaseshan Chandrasekhar
In this paper, we show how to accelerate the performance of running CNNs on encrypted data with GPUs.