Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions

Documenti analoghi

• Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
  di: Chen, Die, et al.
  Pubblicazione: (2024)
• ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction
  di: Duan, Zhongjie, et al.
  Pubblicazione: (2024)
• TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
  di: Sun, Chenxi, et al.
  Pubblicazione: (2023)
• CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
  di: Zhou, Guanghao, et al.
  Pubblicazione: (2025)
• Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
  di: Fan, Mingyuan, et al.
  Pubblicazione: (2023)