MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

Documenti analoghi

• EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models
  di: Chen, Ruoxi, et al.
  Pubblicazione: (2023)
• Watermarking Text Data on Large Language Models for Dataset Copyright
  di: Liu, Yixin, et al.
  Pubblicazione: (2023)
• EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations
  di: Ren, Jie, et al.
  Pubblicazione: (2024)
• Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models
  di: Liu, Yixin, et al.
  Pubblicazione: (2024)
• Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking
  di: Sun, Weixiang, et al.
  Pubblicazione: (2024)