When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

Documenti analoghi

• Negation-Aware Test-Time Adaptation for Vision-Language Models
  di: Han, Haochen, et al.
  Pubblicazione: (2025)
• Data Augmentation in Time Series Forecasting through Inverted Framework
  di: Tan, Hongming, et al.
  Pubblicazione: (2025)
• Unlearning the Noisy Correspondence Makes CLIP More Robust
  di: Han, Haochen, et al.
  Pubblicazione: (2025)
• TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering
  di: Gui, Rui, et al.
  Pubblicazione: (2025)
• When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models
  di: Shamsi, Zafir, et al.
  Pubblicazione: (2026)