arXiv Machine Learning
Revisiting the Provable-Auditable Privacy Gap of DP-SGD
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 22
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv Machine Learning
Jun 15
Let's Ask Gauss: Improved One-Run Privacy Auditing
arXiv:2606. 12733v2 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice.
arXiv AI
Jun 16
Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data
arXiv:2606. 16952v1 Announce Type: cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv Machine Learning
Jun 5
Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run
arXiv:2605. 27292v2 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters.
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.
arXiv Machine Learning
Jul 1
Efficient Public Verification of Private ML via Regularization
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.