When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?

Documenti analoghi

• Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
  di: Jiang, Zhengyuan, et al.
  Pubblicazione: (2025)
• GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
  di: Xie, Yueqi, et al.
  Pubblicazione: (2024)
• Provably Robust Federated Reinforcement Learning
  di: Fang, Minghong, et al.
  Pubblicazione: (2025)
• Certifiably Robust Image Watermark
  di: Jiang, Zhengyuan, et al.
  Pubblicazione: (2024)
• A Transfer Attack to Image Watermarks
  di: Hu, Yuepeng, et al.
  Pubblicazione: (2024)