類似資料

• PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
  著者:: Zhang, Yudong, 等
  出版事項: (2024)
• DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
  著者:: Zhang, Yudong, 等
  出版事項: (2024)
• Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
  著者:: Zhang, Yudong, 等
  出版事項: (2025)
• Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
  著者:: Zhang, Yudong, 等
  出版事項: (2024)
• QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
  著者:: Zhang, Yudong, 等
  出版事項: (2025)