A realisation-level privacy filter for adaptive differential privacy queries that guarantees (ε, δ)-DP and improves utility over standard worst-case composition methods.
R ´enyi differential privacy
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Introduces higher-order Langevin dynamics with auxiliary variables as a defense that mixes randomness early to reduce membership inference success on diffusion models, measured via AUROC and FID on toy and speech data.
citing papers explorer
-
Realisation-Level Privacy Filtering
A realisation-level privacy filter for adaptive differential privacy queries that guarantees (ε, δ)-DP and improves utility over standard worst-case composition methods.
-
Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics
Introduces higher-order Langevin dynamics with auxiliary variables as a defense that mixes randomness early to reduce membership inference success on diffusion models, measured via AUROC and FID on toy and speech data.