arXiv Machine Learning

High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning

The paper addresses the challenge of selecting external datasets for private transfer learning by modeling high‑dimensional regression with heterogeneous sources and a weighted ridge estimator. It relies solely on aggregated statistics and offers privacy guarantees under $ ho$‑zero‑concentrated differential privacy for labels or both features and labels. A deterministic equivalent of test error is derived, enabling optimization of hyperparameters and decision‑making about the utility of private external data without accessing individual records.

arXiv Machine Learning

Oct 2

Certification-Based Differentially Private Learning

The paper extends the abstract gradient training (AGT) framework to provide tighter differential privacy guarantees for both private prediction and private learning. It introduces Abstract Gradient Sampling (AGS) to analyze privacy in continuous, unbounded regression and offers theoretical and empirical evidence that these methods yield tighter bounds than global-sensitivity baselines, even in previously unbounded settings. The authors also demonstrate that their private learning algorithm can outperform standard private learners under comparable conditions.

By Mihnea Ghitu, Matthew Wicker

benchmarks safety

arXiv AI

Sep 30

A Sharp Transition in Data Reconstruction under Differential Privacy

arXiv:2609.37344v1 Announce Type: cross Abstract: Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivat...

By Max Cairney-Leeming, Simone Bombari, Marco Mondelli

safety

arXiv Machine Learning

Aug 18

Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning

arXiv:2303. 07152v3 Announce Type: replace-cross Abstract: Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis.

By T. Tony Cai, Yichen Wang, Linjun Zhang

safety

arXiv Machine Learning

Sep 10

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform

arXiv:2508.04800v2 Announce Type: replace-cross Abstract: We introduce a novel privatization framework for high-dimensional controlled variable selection. Our framework enables rigorous False Discove...

By Yuxuan Tao, Adel Javanmard

safety

arXiv Machine Learning

4d ago

High-Dimensional Asymptotics of Differentially Private PCA

arXiv:2511. 07270v4 Announce Type: replace-cross Abstract: In differential privacy, random noise is introduced to privatize summary statistics of a sensitive dataset before releasing them.

By Youngjoo Yun, Rishabh Dudeja

safety

arXiv AI

Jun 17

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning

arXiv:2503. 10945v3 Announce Type: replace-cross Abstract: Current practices for reporting differential privacy (DP) guarantees for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture.

By Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Flavio P. Calmon, Jamie Hayes, Borja Balle, Antti Honkela

computer-vision benchmarks safety

arXiv AI

Jun 18

Private Learning with Public Feature Conditioning

arXiv:2606. 18773v1 Announce Type: cross Abstract: We study differentially private (DP) regression in settings where each data sample includes public, non-sensitive features -- common in applications such as recommendation and advertising systems.

By Shuli Jiang, Walid Krichene, Nicolas Mayoraz

benchmarks safety

arXiv Machine Learning

Jul 1

Private Rate-Constrained Optimization with Applications to Fair Learning

arXiv:2505. 22703v2 Announce Type: replace Abstract: Many problems in trustworthy ML can be expressed as constraints on prediction rates across subpopulations, including group fairness constraints (demographic parity, equalized odds, etc.

By Mohammad Yaghini, Tudor Cebere, Michael Menart, Aur\'elien Bellet, Nicolas Papernot

safety

arXiv Machine Learning

Sep 11

Label Differential Privacy via Aggregation

arXiv:2310. 10092v4 Announce Type: replace Abstract: This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of \emph{label differential privacy} (label-DP) while maintaining regression task utility.

By Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar, Anshul Nasery, Yukti Makhija, Aravindan Raghuveer

safety

arXiv Machine Learning

Jun 4

DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data

arXiv:2606. 04399v1 Announce Type: new Abstract: In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server.

By Yunsheng Yuan, Xue Xiao, Lina Wang, Feng Li

agents benchmarks safety

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.

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

Related stories