Backpropagation Clipping for Deep Learning with Differential Privacy

1 code implementation • 10 Feb 2022 • Timothy Stevens, Ivoline C. Ngong, David Darais, Calvin Hirsch, David Slater, Joseph P. Near

We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning.

Privacy Preserving Privacy Preserving Deep Learning