2026
DP-LAC: LIGHTWEIGHT ADAPTIVE CLIPPING FOR DIFFERENTIALLY PRIVATE FEDERATED FINE-TUNING OF LANGUAGE MODELS
ICASSP 2026poster
Federated learning (FL) enables the collaborative training of large-scale language models (LLMs) across edge devices while keeping user data on-device. However, FL still exposes sensitive information through client-provided gradients. Differentially private stochastic gradient descent (DP-SGD) mitig…