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.
However, recent work has shown that they are still vulnerable to Backdoor Attacks, Membership Inference Attacks (MIA), and Adversarial Attacks [4]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.