QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models

Ähnliche Einträge

• DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
  von: Zhang, Yudong, et al.
  Veröffentlicht: (2024)
• PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
  von: Zhang, Yudong, et al.
  Veröffentlicht: (2024)
• Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
  von: Zhang, Yudong, et al.
  Veröffentlicht: (2024)
• Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
  von: Zhang, Yudong, et al.
  Veröffentlicht: (2025)
• Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
  von: Fu, Yuhan, et al.
  Veröffentlicht: (2024)