arXiv Machine Learning By Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite, Ioannis Mitliagkas

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

Read the original on arXiv Machine Learning →

arXiv:2605. 11170v2 Announce Type: replace Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model utility, particularly for large-scale deletion requests.

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

arXiv Machine Learning
Jun 30

Efficient Unlearning with Privacy Guarantees

arXiv:2507. 04771v2 Announce Type: replace-cross Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them.

By Josep Domingo-Ferrer, Najeeb Jebreel, David S\'anchez
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.