HAA framework applies hierarchical anti-aesthetic rewards to degrade generation quality and disrupt facial identity in customized diffusion models for privacy protection.
Adversarial example does good: Preventing painting im- itation from diffusion models via adversarial examples,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
VOID defeats mimicry in LDMs via stochasticity manipulation in the diffusion pipeline, raising average FID from 113 to 365 across evaluations.
TS-LFO is a two-stage latent feature optimization method that bypasses state-of-the-art copyright defenses in diffusion-based image customization by restoring semantic consistency in latent space.
citing papers explorer
-
Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization
TS-LFO is a two-stage latent feature optimization method that bypasses state-of-the-art copyright defenses in diffusion-based image customization by restoring semantic consistency in latent space.