DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
Minxin Du, Xiang Yue, Sherman S. M. Chow, Tianhao Wang, Chenyu Huang, Huan Sun · 2023
Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like embedding inversion and sensitive attribute inference. It is also costly in storage and computation when used to fine-tune large pre-trained language models (LMs).