ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models

Documenti analoghi

• DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification
  di: Huang, Chihan, et al.
  Pubblicazione: (2025)
• AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
  di: Dai, Xuelong, et al.
  Pubblicazione: (2023)
• SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion
  di: Lin, Yueqian, et al.
  Pubblicazione: (2023)
• Efficient Denoising using Score Embedding in Score-based Diffusion Models
  di: Na, Andrew S., et al.
  Pubblicazione: (2024)
• SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
  di: Dai, Zeyu, et al.
  Pubblicazione: (2025)