arXiv Machine Learning By Ziniu Liu, Aiping Li

Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity

Read the original on arXiv Machine Learning →

arXiv:2606. 16763v1 Announce Type: cross Abstract: When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP guarantee for the joint output.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jun 1

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

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.

arXiv Machine Learning
Jun 19

Predictability as a Fine-Grained Measure for Privacy

arXiv:2606. 20546v1 Announce Type: new Abstract: Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-accuracy tradeoff.

By Linda Lu, Karthik Sridharan