IREU improves identity unlearning in CPG by offline location of identity features followed by targeted perturbations, outperforming global updates while preserving fidelity for retained identities and generalizing across generators.
Pid: Prompt-independent data protection against latent diffu- sion models.arXiv preprint arXiv:2406.15305, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
VOID defeats mimicry in LDMs via stochasticity manipulation in the diffusion pipeline, raising average FID from 113 to 365 across evaluations.
citing papers explorer
-
IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation
IREU improves identity unlearning in CPG by offline location of identity features followed by targeted perturbations, outperforming global updates while preserving fidelity for retained identities and generalizing across generators.
-
VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models
VOID defeats mimicry in LDMs via stochasticity manipulation in the diffusion pipeline, raising average FID from 113 to 365 across evaluations.