AI RESEARCH
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
arXiv CS.LG
•
ArXi:2606.02563v1 Announce Type: new Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets.