Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

Documenti analoghi

• One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
  di: Balakrishnan, Ravikumar, et al.
  Pubblicazione: (2026)
• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
  di: Waseda, Futa, et al.
  Pubblicazione: (2025)
• Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
  di: Ying, Zonghao, et al.
  Pubblicazione: (2026)
• VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
  di: Balakrishnan, Ravikumar, et al.
  Pubblicazione: (2025)
• VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
  di: Phute, Mansi, et al.
  Pubblicazione: (2025)