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.
1 code implementation • 18 Oct 2022 • Jianxin Wei, Ergute Bao, Xiaokui Xiao, Yin Yang
A classic mechanism for this purpose is DP-SGD, which is a differentially private version of the stochastic gradient descent (SGD) optimizer commonly used for DNN training.
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.