Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

Documenti analoghi

• Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
  di: Khan, Mohammed Safi Ur Rahman, et al.
  Pubblicazione: (2026)
• Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
  di: Li, Bin, et al.
  Pubblicazione: (2025)
• Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
  di: Fazli, Mehrdad, et al.
  Pubblicazione: (2025)
• "See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
  di: Gu, Jihao, et al.
  Pubblicazione: (2025)
• ColorFoil: Investigating Color Blindness in Large Vision and Language Models
  di: Samin, Ahnaf Mozib, et al.
  Pubblicazione: (2024)