Differentially Private Bias-Term Fine-tuning of Foundation Models

arXiv:2210.00036v3 Announce Type: replace-cross
Abstract: We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy is possible under strong privacy constraint, yet requires significant computational overhead or modifications to the network architecture. We propose differentially private bias-term fine-tuning (DP-BiTFiT), which matches the state-of-the-art accuracy for DP algorithms and the efficiency of the standard BiTFiT. DP-BiTFiT is model …

arxiv bias cs.cl cs.cr cs.cv cs.lg fine-tuning foundation replace tuning type