Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models

Ähnliche Einträge

• Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
  von: Liu, Jiaxiang, et al.
  Veröffentlicht: (2025)
• Modest-Align: Data-Efficient Alignment for Vision-Language Models
  von: Liu, Jiaxiang, et al.
  Veröffentlicht: (2025)
• Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
  von: Jia, Xiaojun, et al.
  Veröffentlicht: (2025)
• On the Adversarial Robustness of 3D Large Vision-Language Models
  von: Liu, Chao, et al.
  Veröffentlicht: (2026)
• Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models
  von: Mittal, Atharv, et al.
  Veröffentlicht: (2025)