R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Ähnliche Einträge

• Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
  von: Ying, Zonghao, et al.
  Veröffentlicht: (2024)
• PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
  von: Hussein, Noor, et al.
  Veröffentlicht: (2024)
• Test-Time Attention Purification for Backdoored Large Vision Language Models
  von: Zhang, Zhifang, et al.
  Veröffentlicht: (2026)
• Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
  von: Fu, Jiyuan, et al.
  Veröffentlicht: (2024)
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
  von: Ding, Yi, et al.
  Veröffentlicht: (2025)