Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers

Documenti analoghi

• Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
  di: Gao, Kuofeng, et al.
  Pubblicazione: (2025)
• BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
  di: Yang, Ziqing, et al.
  Pubblicazione: (2026)
• Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  di: Gao, Kuofeng, et al.
  Pubblicazione: (2024)
• Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
  di: Li, Jinmin, et al.
  Pubblicazione: (2024)
• Backdoor Attack with Sparse and Invisible Trigger
  di: Gao, Yinghua, et al.
  Pubblicazione: (2023)