Hypernetwork generates model parameters from one perturbed low-dimensional private dataset embedding, yielding higher utility than DP-SGD under fixed privacy budget in synthetic theory and lower FID in LoRA diffusion fine-tuning.
arXiv preprint arXiv:2210.00968 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.
citing papers explorer
-
Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
Hypernetwork generates model parameters from one perturbed low-dimensional private dataset embedding, yielding higher utility than DP-SGD under fixed privacy budget in synthetic theory and lower FID in LoRA diffusion fine-tuning.
-
Auditing Training Data in Generative Music Models via Black-Box Membership Inference
Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.