One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

Documenti analoghi

• AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
  di: Li, Lin, et al.
  Pubblicazione: (2023)
• Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
  di: Kong, Dehong, et al.
  Pubblicazione: (2024)
• When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
  di: Fontana, Maxime, et al.
  Pubblicazione: (2023)
• Adversarial Prompt Tuning for Vision-Language Models
  di: Zhang, Jiaming, et al.
  Pubblicazione: (2023)
• NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
  di: Zhang, Jiaming, et al.
  Pubblicazione: (2025)