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 Machine Learning
Sep 23
Optimizing Canaries for Privacy Auditing with Metagradient Descent
The paper investigates black-box privacy auditing for differentially private learning algorithms, focusing on DP‑SGD. It introduces a method that optimizes the auditor’s canary set using metagradient descent, improving empirical lower bounds on privacy parameters compared to prior canary designs. The approach is shown to be DP‑SGD agnostic and efficient, with optimized canaries for small models remaining effective for larger DP‑SGD models.
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 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.
arXiv AI
Oct 21
Reliable Estimation of Differential Privacy under Selection Bias
The paper addresses a flaw in differential privacy audits where selection bias in Membership Inference Attacks leads to overestimated lower bounds on privacy leakage. By applying statistical correction methods, the authors demonstrate that uncorrected audits can violate theoretical privacy guarantees up to four times more often than claimed, while corrected audits maintain valid bounds at the nominal confidence level.
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.