Documenti analoghi

• QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
  di: Zhang, Yudong, et al.
  Pubblicazione: (2025)
• Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
  di: Zhang, Yudong, et al.
  Pubblicazione: (2025)
• DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
  di: Zhang, Yudong, et al.
  Pubblicazione: (2024)
• PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
  di: Zhang, Yudong, et al.
  Pubblicazione: (2024)
• MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
  di: Ding, Wei, et al.
  Pubblicazione: (2026)