arXiv Machine Learning August 11, 2026 By Murat Bilgehan Ertan, Marten van Dijk

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

Read the original on arXiv Machine Learning →

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.

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

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 3

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

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.

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

safety

arXiv Machine Learning

Jul 28

DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton

arXiv:2607. 23649v1 Announce Type: new Abstract: Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-aware prediction.

By Nour Jamoussi, Ikram Dridi, Giuseppe Serra, Marios Kountouris

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

Jul 23

End-to-End Differential Privacy in Training Deep Neural Network Classifiers

arXiv:2607. 19580v1 Announce Type: new Abstract: Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from the parameters of the resulting model.

By Huaiyuan Rao, Calvin Hawkins, Alexander Benvenuti, Matthew Hale

benchmarks safety

arXiv Machine Learning

Jul 23

Differentially Private Neural Network Training Under the Hidden State Assumption

arXiv:2407. 08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning.

By Ding Chen, Haochen Luo, Xiaofei Wang, Chen Liu

benchmarks safety

Related stories

Private Prediction via PAC Privacy

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

DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton

Private Rate-Constrained Optimization with Applications to Fair Learning

End-to-End Differential Privacy in Training Deep Neural Network Classifiers

Differentially Private Neural Network Training Under the Hidden State Assumption