arXiv Machine Learning June 3, 2026 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jun 8

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning

arXiv:2412. 09119v3 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment.

By Youssef Allouah, Joshua Kazdan, Rachid Guerraoui, Sanmi Koyejo

safety

arXiv Machine Learning

Aug 11

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

arXiv:2601. 10237v3 Announce Type: replace Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood.

By Murat Bilgehan Ertan, Marten van Dijk

safety

arXiv Machine Learning

Sep 1

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...

By Saloni Modi, Srivi Balaji, Yusong Zhu, Gautam Kamath, Kevin Tian

benchmarks safety

arXiv Machine Learning

Jun 15

Private Prediction via PAC Privacy

arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.

By Xiaochen Zhu, Mayuri Sridhar, Srinivas Devadas

safety

arXiv Machine Learning

Jun 2

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

arXiv:2606. 02563v1 Announce Type: new Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity.

By Farhin Farhad Riya, Olivera Kotevska, Jinyuan Stella Sun

safety

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

safety

One email a morning, machine-written

Related stories

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

Revisiting the Provable-Auditable Privacy Gap of DP-SGD

Private Prediction via PAC Privacy

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning

Efficient Unlearning with Privacy Guarantees